DETAILED ACTION
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Continued Examination Under 37 CFR 1.114
A request for continued examination under 37 CFR 1.114, including the fee set forth in 37 CFR 1.17(e), was filed in this application after final rejection. Since this application is eligible for continued examination under 37 CFR 1.114, and the fee set forth in 37 CFR 1.17(e) has been timely paid, the finality of the previous Office action has been withdrawn pursuant to 37 CFR 1.114. Applicant's submission filed on16 March 2026 has been entered.
2. Applicant’s submission filed 16 March 2026 [hereinafter Response] has been entered, where:
Claims 1, 14, 15, and 20 have been amended.
Claims 1-20 are pending.
Claims 1-20 are rejected.
Claim Rejections -35 U.S.C. § 112
3. The following is a quotation of 35 U.S.C. 112(b):
(b) CONCLUSION.—The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention.
4. Claims 1-14 are rejected under 35 U.S.C. 112(b) as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor regards as the invention.
Claim 1, line 3, recites the limitation "a machine learning job.” It is unclear whether this limitation is either intended to draw antecedence from the term “a machine vision job” of claim 1, line 2, or intended to be a separate and distinct instance of the limitation. Accordingly, the claim is indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor regards as the invention.
Claim 1, line 17, recites “the machine vision camera.” There is insufficient antecedent basis for this limitation in the claim.
Claim 1, line 21, recites the limitation “a run-time image of a target object.” It is unclear whether this limitation is either intended to draw antecedence from the term “a run-time image of a target object” of claim 1, lines 18-19, or is intended to be a separate and distinct instance of the limitation. Accordingly, the claim is indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor regards as the invention.
Claim 8, lines 9-10 & 24, recite “the machine vision camera.” There is insufficient antecedent basis for this limitation in the claim.
Claim 8, lines 6 & 13-14, each recites the limitation "a machine vision job.” It is unclear whether this limitation is either intended to draw antecedence from the term “a machine vision job” of claim 8, line 2, or intended to be a separate and distinct instance of the limitation. Accordingly, the claim is indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor oar a joint inventor regards as the invention.
Claim 8, line 25, recites “the run-time image.” There is insufficient antecedent basis for this limitation in the claim.
Claim 8, line 26, recites “a machine vision camera.” It is unclear whether this limitation is intended to actually draw antecedence from the earlier term “the machine vision camera” of claim 8, lines 9-10 & 24, or intended to be a separate and distinct instance of the limitation. Accordingly, the claim is indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor regards as the invention.
Claims 2-7 depend directly or indirectly from claim 1. Claims 9-14 depend directly or indirectly from claim 8. Claims 2-7 and 9-14 are rejected as depending from a rejected claim; further, the claims fail to cure the deficiencies of claims 1 and 8.
Claim Rejections - 35 U.S.C. § 101
5. 35 U.S.C. § 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
6. Claims 1-20 are rejected under 35 U.S.C. § 101 because the claimed invention is directed to an abstract idea without significantly more.
Claim 1 recites a method which is a process, and thus one of the statutory categories of patentable subject matter. (35 U.S.C. § 101).
However, under Step 2A Prong One, the claim recites the limitations of
“[(a.2)]1 (b) generating . . . prediction values corresponding to an analysis of each training image of the set of training images,” “[(a.4)] (d) adjusting the machine vision job based on the change value,” “[(a.5)] (e) iteratively performing steps (a)-(e) until the ML model determines that the prediction values satisfy a prediction threshold,” and “[(b)] inspecting a target object by: . . . [(b.3)] executing, on the machine vision camera, the trained machine vision job to analyze a run-time image of a target object.” These activities of “[(a.2)] (b) generating,” “[(a.4)] (d) adjusting,” “[(a.5)] (e) determines,” and “[(b)] inspecting” contain limitations that can practically be performed in the human mind, including, for example, observations, evaluations, judgments, and opinions, and accordingly, recite a mental process, (MPEP § 2106.04(a)(2) sub III), which is one of the groupings of abstract ideas. (MPEP § 2106.04(a)(2)). Thus, claim 1 recites an abstract idea.
Under Step 2A Prong Two, the claim as a whole is not integrated into a practical application, because the additional elements recited in the claim beyond the identified judicial exception include a “machine vision job including one or more machine vision tools,” a “machine vision camera,” which are recited at high-level of generality, and thus, generic computer components used to implement the abstract idea, (MPEP § 2106.05(f)), that does not serve to integrate the abstract idea into a practical application. The claim also recites a “machine learning model,” in which the claim does not provide any details about how the model operates to output a change value from a prediction value input. Accordingly, the machine learning model is recited at a high-level of generality, and thus a generic computer component used to implement the abstract idea, (MPEP § 2106.05(f)), that does not serve to integrate the abstract idea into a practical application.
The claim also recites “[(a)] training a machine vision job by: [(a.1)] (a) receiving, at a machine vision job including one or more machine vision tools, a set of training images,” which is a pre-processing, insignificant extra-solution activity of mere data gathering, (MPEP § 2106.05(f)), that does not serve to integrate the abstract idea into a practical application.
The claim also recites “[(a)] training a machine vision job by: . . . [(a.3)] (c) inputting the prediction values into a machine learning (ML) model . . . and output a change value corresponding to the machine vision job,” which is the use of a generic computer component (machine learning model) to implement the abstract idea, (MPEP § 2106.05(f)), that does not serve to integrate the abstract idea into a practical application.
The claim also recites more details or specifics to the additional element of “[(a.3)] inputting . . . and output a change value,” where “[(a.3.1)] the change value representing an adjustment to the one or more parameters of the machine vision job to eliminate an incorrect outcome of the analysis,” and accordingly, is merely more specific to the additional element.
The claim also recites “[(b)] inspecting a target object by: [(b.1)] deploying the trained machine vision job on the machine vision camera,” which is a pre-processing insignificant extra-solution activity of sending data (trained vision job) in preparation of execution, (MPEP § 2106.05(g)), that does not serve to integrate the abstract idea into a practical application. The claim further recites “[(b)] inspecting a target object by: . . . [(b.2)] imaging the target object with the machine vision camera to capture a run-time image of the target object,” which is the use of a generic computer component (machine vision camera) to implement the abstract idea, (MPEP § 2106.05(f)), that that does not serve to integrate the abstract idea into a practical application. Still further, the claims recite “[(b)] inspecting a target object by: . . . “[(b.4)] outputting, by the trained machine vision job, an inspection result,” which is a post-processing insignificant extra-solution activity of outputting results the abstract idea, (MPEP § 2106.05(g)), that does not serve to integrate the abstract idea into a practical application. Therefore, claim 1 is directed to the abstract idea.
Finally, under Step 2B, the additional elements, taken alone or in combination, do not represent significantly more than the abstract idea itself. The additional elements recited in the claim beyond the identified judicial exception include additional elements recited in the claim beyond the identified judicial exception include a “machine vision job including one or more machine vision tools,” a “machine vision camera,” which are recited at high-level of generality, and thus, generic computer components used to implement the abstract idea, (MPEP § 2106.05(f)), that does not amount to significantly more than the abstract idea. The claim also recites a “machine learning model,” in which the claim does not provide any details about how the model operates to output a change value from a prediction value input. Accordingly, the machine learning model is recited at a high-level of generality, and thus a generic computer component used to implement the abstract idea, (MPEP § 2106.05(f)), that does not amount to significantly more than the abstract idea.
The claim also recites “[(a)] training a machine vision job by:” [(a.1)] (a) receiving, at a machine vision job including one or more machine vision tools, a set of training images,” which is a well-understood, routine, and conventional activity of receiving data over a network, (MPEP § 2106.05(d) sub II.i), that does not amount to significantly more than the abstract idea.
“[(a.3)] (c) input the prediction values into a machine learning (ML) model . . . and output a change value corresponding to the machine vision job,” which is the use of a generic computer component (machine learning model) to implement the abstract idea, (MPEP § 2106.05(f)), that does not amount to significantly more than the abstract idea.
The claim also recites more details or specifics to the additional element of “[(a.3)] inputting . . . and output a change value,” where “[(a.3.1)] the change value representing an adjustment to the one or more parameters of the machine vision job to eliminate an incorrect outcome of the analysis,” and accordingly, is merely more specific to the additional element.
The claim also recites “[(b)] inspecting a target object by: [(b.1)] deploying the trained machine vision job on the machine vision camera,” which is a well-understood, routine, and conventional activity of sending data (trained vision job) over a network, (MPEP § 2106.05(d) sub II.1), that does not amount to significantly more than the abstract idea. The claim further recites “[(b)] inspecting a target object by: . . . [(b.2)] imaging the target object with the machine vision camera to capture a run-time image of the target object,” which is the use of a generic computer component (machine vision camera) to implement the abstract idea, (MPEP § 2106.05(f)), that does not amount to significantly more than the abstract idea. Still further, the claims recite “[(b)] inspecting a target object by: . . . “[(b.4)] outputting, by the trained machine vision job, an inspection result,” which is a well-understood, routine, and conventional activity of outputting a result of the abstract idea over a network, (MPEP § 2106.05(d) sub II.i), that does not amount to significantly more than the abstract idea. Therefore, claim 1 is subject-matter ineligible.
Claim 8 recites a system which is a product, and thus one of the statutory categories of patentable subject matter. (35 U.S.C. § 101).
However, under Step 2A Prong One, the claim recites the limitations of “[(a.2)] (b) generating, by one or more machine vision tools of a machine vision job, prediction values corresponding to an analysis of each training image of the set of training images,” “[(a.4)] (d) adjusting the machine vision job based on the change value,” and “[(a.5)] (e) iteratively performing steps (a)-(e) until the ML model determines that the prediction values satisfy a prediction threshold.” These activities of “[(a.2)] (b) generating,” “[(a.4)] (d) adjusting,” and “[(a.5)] (e) determines,” contain limitations that can practically be performed in the human mind, including, for example, observations, evaluations, judgments, and opinions, and accordingly, recite a mental process, (MPEP § 2106.04(a)(2) sub III), which is one of the groupings of abstract ideas. (MPEP § 2106.04(a)(2)). Thus, claim 1 recites an abstract idea.
Under Step 2A Prong Two, the claim as a whole is not integrated into a practical application, because the additional elements recited in the claim beyond the identified judicial exception include a “computing device configured to train a machine vision job,” “one or more processors,” a “non-transitory computer-readable memory coupled to the machine vision camera and the one or more processors, the memory storing instructions thereon that, when executed by the one or more processors, cause,” and a “machine vision camera,” which are recited at high-level of generality, and thus, generic computer components used to implement the abstract idea, (MPEP § 2106.05(f)), that does not serve to integrate the abstract idea into a practical application. The claim also recites a “machine learning model,” in which the claim does not provide any details about how the model operates to output a change value from a prediction value input. Accordingly, the machine learning model is recited at a high-level of generality, and thus a generic computer component used to implement the abstract idea, (MPEP § 2106.05(f)), that does not serve to integrate the abstract idea into a practical application.
The claim also recites “[(a)] a computing device configured to train a machine vision job, . . . including: [(a.1)] (a) receive a set of training images,” which is a pre-processing, insignificant extra-solution activity of mere data gathering, (MPEP § 2106.05(g)), that does not serve to integrate the abstract idea into a practical application.
The claim also recites “[(a)] a computing device configured to train a machine vision job, . . . including: . . . [(a.3)] (c) input the prediction values into a machine learning (ML) model . . . and output a change value corresponding to the machine vision job,” which is the use of a generic computer component (machine learning model) to implement the abstract idea, (MPEP § 2106.05(f)), that does not serve to integrate the abstract idea into a practical application.
The claim also recites more details or specifics to the additional element of “[(a.3)] input . . . and output a change value,” where “[(a.3.1)] the change value representing an adjustment to the one or more parameters of the machine vision job to eliminate an incorrect outcome of the analysis,” and accordingly, is merely more specific to the additional element.
The claim recites [(a)] a computing device configured to train a machine vision job, . . . including: . . . [(a.6)] transmit the machine vision job to the machine vision camera for execution on the run-time image,” which is the pre-processing insignificant extra-solution activity of sending the result of the abstract idea to a generic computer component (machine vision camera), (MPEP § 2106.05(g)), that does not serve to integrate the abstract idea into a practical application.
The claim also recites “[(b)] a machine vision camera configured to: [(b.1)] receive the trained machine vision job,” and “[(b.4)] produce, via the trained machine vision job, an inspection result,” which are pre-processing and post-processing insignificant extra-solution activities of receiving and receiving data of the abstract idea, (MPEP § 2106.05(g)), that does not serve to integrate the abstract idea into a practical application.
The claim further recites “[(b)] a machine vision camera configured to: . . . [(b.2)] capture a run-time image of the target object,” and “[(b.3)] execute the trained machine vision job on the run-time image,” which is the use of generic computer components (machine vision camera, trained vision job) to implement that abstract idea (MPEP § 2106.05(f)), that does not serve to integrate the abstract idea into a practical application. Therefore, claim 8 is directed to the abstract idea.
Finally, under Step 2B, the additional elements, taken alone or in combination, do not represent significantly more than the abstract idea itself. The additional elements recited in the claim beyond the identified judicial exception include a “computing device configured to train a machine vision job,” “one or more processors,” a “non-transitory computer-readable memory coupled to the machine vision camera and the one or more processors, the memory storing instructions thereon that, when executed by the one or more processors, cause,” and a “machine vision camera,” which are recited at high-level of generality, and thus, generic computer components used to implement the abstract idea, (MPEP § 2106.05(f)), that does not amount to significantly more than the abstract idea. The claim also recites a “machine learning model,” in which the claim does not provide any details about how the model operates to output a change value from a prediction value input. Accordingly, the machine learning model is recited at a high-level of generality, and thus a generic computer component used to implement the abstract idea, (MPEP § 2106.05(f)), that does not amount to significantly more than the abstract idea.
The claim also recites “[(a)] a computing device configured to train a machine vision job, . . . including: [(a.1)] (a) receive a set of training images,” which is a pre-processing, insignificant extra-solution activity of mere data gathering, (MPEP § 2106.05(g)), which is a well-understood, routine, and conventional activity of receiving data over a network, (MPEP § 2106.05(d) sub II.i), that does not amount to significantly more than the abstract idea.
The claim also recites “[(a)] a computing device configured to train a machine vision job, . . . including: . . . [(a.3)] (c) input the prediction values into a machine learning (ML) model . . . and output a change value corresponding to the machine vision job,” which is the use of a generic computer component (machine learning model) to implement the abstract idea, (MPEP § 2106.05(f)), that does not amount to significantly more than the abstract idea.
The claim also recites more details or specifics to the additional element of “[(a.3)] input . . . and output a change value,” where “[(a.3.1)] the change value representing an adjustment to the one or more parameters of the machine vision job to eliminate an incorrect outcome of the analysis,” and accordingly, is merely more specific to the additional element.
The claim recites [(a)] a computing device configured to train a machine vision job, . . . including: . . . [(a.6)] transmit the machine vision job to the machine vision camera for execution on the run-time image,” which is the well-understood, routine, and conventional activity of transmitting data over a network, (MPEP § 2106.05(d) sub II.i), that does not amount to significantly more than the abstract idea.
The claim also recites “[(b)] a machine vision camera configured to: [(b.1)] receive the trained machine vision job,” and “[(b.4)] produce, via the trained machine vision job, an inspection result,” which are well-understood, routine, and conventional activities of receiving or transmitting data over a network, (MPEP § 2106.05(d) sub II.i), that does not amount to significantly more than the abstract idea.
The claim further recites “[(b)] a machine vision camera configured to: . . . [(b.2)] capture a run-time image of the target object,” and “[(b.3)] execute the trained machine vision job on the run-time image,” which is the use of generic computer components (machine vision camera, trained vision job) to implement that abstract idea (MPEP § 2106.05(f)), that does not amount to significantly more than the abstract idea. Therefore, claim 8 is subject-matter ineligible.
Claim 15 recites a tangible machine-readable medium, which is a product, and thus one of the statutory categories of patentable subject matter. (35 U.S.C. § 101).
However, under Step 2A Prong One, the claim recites the limitations of “(b) generate . . . prediction values corresponding to the set of training images,” “(d) adjust the machine vision job based on the change value,” and “(e) iteratively perform steps (a)-(e) until the ML model determines that the prediction values satisfy a prediction threshold.” These limitations recite a mental process, (MPEP § 2106.04(a)(2) sub III), which is one of the groupings of abstract ideas. (MPEP § 2106.04(a)(2)). Thus, claim 15 recites an abstract idea.
Under Step 2A Prong Two, the claim as a whole is not integrated into a practical application, because the additional elements recited in the claim beyond the identified judicial exception include a machine vision camera, and a tangible machine-readable medium,” which are generic computer components used to implement the abstract idea, (MPEP § 2106.05(f)), that does not integrate the abstract idea into a practical application. The claim also recites a machine learning model, in which the claim does not provide any details about how the model operates to output a change value from a prediction value input, and accordingly, the machine learning model is a generic computer component used to implement the abstract idea, (MPEP § 2106.05(f)), that does not serve to integrate the abstract idea into a practical application. The claim also recites “(c) input the prediction values into a machine learning (ML) model . . . and output a change value corresponding to the machine vision job,” which is the use of a generic computer component (machine learning model) to implement the abstract idea, (MPEP § 2106.05(f)), that does not serve to integrate the abstract idea into a practical application. The claim recites more details or specifics to the additional element of “output a change value,” where “the change value representing an adjustment to the one or more parameters of the machine vision job to eliminate an incorrect outcome of the analysis,” and accordingly, is merely more specific to the additional element. The claim also recites the limitations of “(a) receive a set of training images,” and “[(f)] transmit the machine vision job to the machine vision camera . . . without the ML model and output an inspection result,” which are insignificant extra-solution activities of mere data gathering, (MPEP § 2106.05(g)), that does not serve to integrate the abstract idea into a practical application. Therefore, claim 15 is directed to the abstract idea.
Finally, under Step 2B, the additional elements, taken alone or in combination, do not represent significantly more than the abstract idea itself. The additional elements recited in the claim beyond the identified judicial exception include a machine vision camera, and a tangible machine-readable medium,” which are generic computer components used to implement the abstract idea, (MPEP § 2106.05(f)), that does not amount to significantly more than the abstract idea. The claim also recites a machine learning model, in which the claim does not provide any details about how the model operates to output a change value from a prediction value input, and accordingly, the machine learning model is a generic computer component used to implement the abstract idea, (MPEP § 2106.05(f)), that does not amount to significantly more than the abstract idea. The claim also recites “(c) input the prediction values into a machine learning (ML) model . . . and output a change value corresponding to the machine vision job,” which is the use of a generic computer component (machine learning model) to implement the abstract idea, (MPEP § 2106.05(f)), that does not amount to significantly more than the abstract idea. The claim recites more details or specifics to the additional element of “output a change value,” where “the change value representing an adjustment to the one or more parameters of the machine vision job to eliminate an incorrect outcome of the analysis,” and accordingly, is merely more specific to the additional element. The claim also recites the limitations of “(a) receive a set of training images,” and “transmit the machine vision job to the machine vision camera . . . without the ML model and output an inspection result,” which are well-understood, routine, and conventional activities of receiving or transmitting data over a network, (MPEP § 2106.05(d) sub II.i), that does not amount to significantly more than the abstract idea. Therefore, claim 15 is subject matter ineligible.
Claims 2-4 depend directly or indirectly from claim 1. Claims 9-11 depend directly or indirectly from claim 8. Claims 16-18 depend directly or indirectly from claim 15. The claims recite more details or specifics to the abstract idea of a “adjusting the machine vision job [including one or more machine vision tools]” (claims 2, 9, and 16: each of the one or more machine vision tools includes one or more parameter values, and adjusting the machine vision job based on the change value further comprises: adjusting a first parameter value of the one or more parameter values for a first machine vision tool of the one or more machine vision tools;” claims 3, 10, and 17: the one or more machine vision tools includes at least two machine vision tools, and adjusting the machine vision job based on the change value includes adjusting an execution order of the at least two machine vision tools within the machine vision job”; claims 4, 11, and 18: “wherein the at least two machine vision tools include at least one of: (i) an edge detection tool, (ii) a pattern matching tool, (iii) a segmentation tool, (iv) a thresholding tool, (v) a barcode decoding tool, (vi) an optical character recognition tool, (vii) an object tracking tool, (viii) an object detection tool, (ix) a color analysis algorithm, or (x) an image filtering tool”), and accordingly, are merely more specific to the abstract idea. The abstract idea of these claims are not integrated into a practical application, (see MPEP § 2106.05(d)), nor do they amount to significantly more than the abstract idea, (MPEP § 2106.05(d)), because the claims recite no more than the abstract idea. Therefore, claims 2-4, 9-11, and 16-18 are subject-matter ineligible.
Claim 5 depends from claim 1. Claim 12 depends from claim 8. The claims recite more details or specifics to the abstract idea of “the ML model determines that the prediction values satisfy a prediction threshold,” (claims 5 and 8: wherein the ML model uses a cost function to determine whether or not the prediction values satisfy the prediction threshold”), and accordingly, are merely more specific to the abstract idea. The abstract idea of these claims are not integrated into a practical application, (see MPEP § 2106.05(d)), nor do they amount to significantly more than the abstract idea, (MPEP § 2106.05(d)), because the claims recite no more than the abstract idea. Therefore, claims 5 and 12 are subject-matter ineligible.
Claims 6 and 7 depend directly or indirectly from claim 1. Claims 13 and 14 depend directly or indirectly from claim 8. Claims 19 and 20 depend directly or indirectly from claim 15. The claims recite more details or specifics to the additional element of “receiving a set of training images,” (claims 6, 13, and 19: wherein the set of training images includes image labels indicating an inspection result corresponding to each training image, and inputting the prediction values into the ML model further comprises: inputting the prediction values and the image labels into the ML model in order to output the change value;” claims 7, 14, and 20: “wherein the machine vision camera executes the trained machine vision job to analyze the run-time image without inputting run-time image data into the ML model, and the inspection result corresponds to whether or not the run-time image data satisfies a set of inspection criteria”), and accordingly, are merely more specific to the additional element. The abstract idea of these claims are not integrated into a practical application, (see MPEP § 2106.05(d)), nor do they amount to significantly more than the abstract idea, (MPEP § 2106.05(d)), because the claims recite no more than the abstract idea. Therefore, claims 6, 7, 13, 14, 19, and 20 are subject-matter ineligible.
Claim Rejections - 35 U.S.C. § 103
7. The following is a quotation of 35 U.S.C. §103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
8. The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. §103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
9. Claims 1-20 are rejected under 35 U.S.C. §§103 as being unpatentable over US Published Application 20220222926 to Gladisch et al. [hereinafter Gladisch] in view US Published Application 20200166909 to Noone et al. [hereinafter Noone].
Regarding claim 1, Gladisch teaches [a] method for implementing a hybrid machine vision model (Gladisch ¶ 0002 teaches “a computer-implemented method for providing a set of training data, a computer-implemented method for training a computer vision model”; Gladisch ¶ 0135 & Fig. 6 teaches “data processing apparatus 300 is a personal computer, server, cloud-based server, or embedded computer. [(that is, a method for implementing a hybrid machine vision model)]”) to optimize performance of a machine vision job, the method comprising:
[(a)] training a machine vision job (Gladish ¶ 0013 teaches “images chosen as training data according to the second visual parameter specification may be useful for training a computer vision model [(that is, training a machine vision job)]”) by:
[(a.1)] (a) receiving, at a machine vision job including one or more machine vision tools (Gladisch ¶ 0003 teaches “[c]omputer vision can process inputs from any interaction between at least one detector and the environment of that detector [(that is, a machine vision job)]. The environment may be perceived by the at least one detector as a scene or a succession of scenes. In particular, interaction may result from at least one camera, a multi-camera system, a RADAR system or a LIDAR system;” Gladisch ¶ 0137 teaches that, “[i]n an example, the apparatus 300 is an automotive embedded computer comprised in a vehicle, in which case the automotive embedded computer may be connected to sensors and actuators present in the vehicle. . . . [T]he output interface 340 of the apparatus 300 may interface with one or more of a plurality of brake actuators, throttle actuators, fuel mixture or fuel air mixture actuators, a turbocharger controller, a battery management system, the car lighting system or entertainment system, and the like [(that is, “actuators” are a machine vision job including one or more machine vision tools)]”)), a set of training images (Gladisch ¶ 0013 teaches “images chosen as training data according to the second visual parameter specification may be useful for training a computer vision model [(that is, receiving . . . a set of training images )]”);
[(a.2)] (b) generating, by the one or more machine vision tools, prediction values corresponding to an analysis of each training image of the set of training images (Gladisch ¶ 0066 teaches “obtaining 104 a first visual parameter specification comprising at least one initial visual parameter set, wherein an item of visual data [(that is, each training image)] provided based on the extent of the at least one visual parameter set is capable of affecting [(that is, “based on the extent of . . . affecting” is generating . . . prediction values corresponding to an analysis)] a classification or regression performance of the computer vision model [(that is, generating, by the one or more machine vision tools, prediction values corresponding to an analysis of each training image of the set of training images)]”);
[(a.3)] (c) inputting the prediction values into a machine learning (ML) model configured to receive prediction values and output a change value corresponding to one or more parameters of the machine vision job (Gladisch ¶ 0085 & Fig. 2, teaches providing “visual parameters [that] are oversampled at regions that are suspected to define performance corners of the computer vision model 16 [Examiner annotations in dashed-line text boxes]:”
PNG
media_image1.png
704
1245
media_image1.png
Greyscale
Gladisch ¶ 0091 teaches “[t]he result is a plurality of performance scores according to the sampled values of the visual parameter specification [(that is, inputting the prediction values into a machine learning (ML) model configured to receive prediction values)]”; Gladisch ¶¶ 0092-93 teaches “obtaining a plurality of performance scores further comprises generating, using the computer vision model, a plurality of predictions of elements of observed scenes in the subset of items of visual data. . . to thus obtain the plurality of performance scores [(that is, “performance scores” is output a change value corresponding to one or more parameters of the machine vision job)]”),
[(a.3.1)] the change value representing an adjustment to the one or more parameters of the machine vision job to eliminate an incorrect outcome of the analysis (Gladisch ¶ 0099 teaches “refining step 45 uses the results of the global sensitivity analysis 19 [(that is, the “result” is the change value)] to modify at least one initial visual parameter of the visual parameter specification [(that is, the change value representing an adjustment to the one or more parameters of the machine vision job to eliminate an incorrect outcome of the analysis)], to thus yield a second visual parameter specification”);
[(a.4)] (d) adjusting the machine vision job based on the change value (Gladisch ¶ 0099 teaches “refining step 45 uses the results of the global sensitivity analysis 19 [(that is, the “result” is the change value)] to modify at least one initial visual parameter of the visual parameter specification, to thus yield a second visual parameter specification [(that is, “yield a second visual parameter specification” is adjusting the machine vision job based on the change value)]”);
[(a.5)] (e) iteratively performing steps (a)-(e) until the ML model determines that the prediction values satisfy a prediction threshold (Gladisch ¶ 0098 teaches “[t]he testing step 17 and the global sensitivity analysis 19 and/or retraining the computer vision model 16 can be repeated. Optionally, the performance scores and variances of the performance score are tracked during such training iterations [(that is, iteratively performing steps (a)- (e) until the ML model determines that the prediction values satisfy a prediction threshold)]. The training iterations are stopped when the variances of the performance score appear to have settled (stopped changing significantly) [(that is, “settled” is the prediction values satisfy a prediction threshold)]”); and
* * *
Though Gladisch teaches improving the visual parameter specification according to a sensitivity analysis of a computer vision model used in object detection and/or recognition, Gladisch, however, does not explicitly teach –
* * *
[(b)] inspecting a target object by:
[(b.1)] deploying the trained machine vision job on the machine vision camera:
[(b.2)] imaging the target object with the machine vision camera to capture a run-time image of the target object;
[(b.3)] executing, on the machine vision camera, the trained machine vision job to analyze a run-time image of a target object; and
[(b.4)] outputting, by the trained machine vision job, an inspection result.
But Noone teaches –
* * *
[(b)] inspecting a target object (Noone ¶ 0178 teaches “[a]daptive [medial axis transformation (MAT)] path planning algorithms are able to automatically generate path patterns with varying step-over distances by analyzing the part geometry [(that is, inspecting)] to achieve better part quality (void-free deposition), accuracy at the boundary, and efficient use of material {(that is, inspecting a target object)]”) by:
[(b.1)] deploying the trained machine vision job on the machine vision camera (Noone, Fig. 1, teaches a single integrated system [Examiner annotations in dashed-line text boxes]:
PNG
media_image2.png
719
1067
media_image2.png
Greyscale
Noone ¶ 0005 teaches “the method is implemented using . . . a single integrated system [(that is, machine vision camera)] comprising a manufacturing apparatus, a sensor, and a processor”; Noone ¶ 0007 teaches “the processor is further programmed to provide a predicted optimal set of one or more starting manufacturing process control parameters that is derived using the machine learning algorithm”; Noone ¶ 0212 teaches “[m]achine vision systems provide imaging-based automatic inspection and analysis for a variety of industrial inspection, process control, and robot guidance applications, and may comprise any of a variety of image sensors or cameras, light sources or illumination systems, and additional imaging optical components, as well as processors and image processing software [(that is, the machine vision camera)]”);
[(b.2)] imaging the target object with the machine vision camera to capture a run-time image of the target object (Noone ¶ 0008 teaches “automated classification of manufactured object defects (i.e., in real time as the object is being fabricated) [(that is, being in “real-time” is a run-time)], the methods comprising: . . . providing one or more sensors, wherein the one or more sensors provide real-time data for one or more manufactured object properties; Noone ¶ 0197 teaches ”[a]ny of a variety of process monitoring tools known to those of skill in the art may be used including, but not limited to, . . . image sensors and machine vision systems, . . . . In some embodiments, the process characterization sensors may comprise one or more sensors, cameras, or imaging systems that detect electromagnetic radiation that is reflected, scattered, absorbed, transmitted, or emitted by the object [(that is, imaging the target object with the machine vision camera to capture a run-time image of the target object)]”;
[Examiner notes that in the execution of processes, the broadest reasonable interpretation of the term “run-time” is synonymous to the term real-time of the cited art of Noone, which is not inconsistent with the Applicant’s Specification (MPEP § 2111)]));
[(b.3)] executing, on the machine vision camera, the trained machine vision job to analyze a run-time image of a target object (Noone ¶ 0212 teaches “[m]achine vision systems provide imaging-based automatic inspection and analysis for a variety of industrial inspection, process control, and robot guidance applications, and may comprise any of a variety of image sensors or cameras, light sources or illumination systems, and additional imaging optical components, as well as processors and image processing software”; Noone ¶ 0246 teaches “support vector machines are supervised learning algorithms used for classification and regression analysis of object defect classification data or manufacturing process control [(that is, executing, on the machine vision camera, the trained machine vision job to analyze a run-time image of a target object)]”); and
[(b.4)] outputting, by the trained machine vision job, an inspection result (Noone ¶ 0234 teaches “the part is monitored in real-time using an automated object defect classification system as disclosed herein. Once the current build state of the part has been determined, a reinforcement learning algorithm uses the current state information, sj, and the model developed using past training data to predict a proposed action, aj+1, (e.g., a set or sequence of process control parameter adjustments) that will maximize a reward function [(that is, “state information sj” is outputting, by the trained machine vision job, an inspection result)]”).
Gladisch and Noone are from the same or similar field of endeavor. Gladisch teaches improving the visual parameter specification according to a sensitivity analysis of a computer vision model. Noone teaches subtraction of a reference data set from the sensor data to increase contrast between normal and defective features of an object.
Thus, it would have been obvious to a person having ordinary skill in the art as of the effective filing date of the Applicant’s invention to modify Gladisch pertaining to sensitivity analysis of a computer vision model with the run-time image analysis of a target object and output an inspection result of Noone.
The motivation to do so is to “make adjustment(s) to one or more process control parameters in order to improve, for example, the dimensional accuracy of the layer, layer surface finish and/or adhesion properties, and/or the overall efficiency of the deposition process.” (Noone ¶ 0210).
Regarding claim 8, Gladisch teaches [a] computer system for implementing a hybrid machine vision model (Gladisch ¶ 0003 teaches “Computer vision systems are finding increasing application to the automotive or robotic vehicle field. Computer vision can process inputs from any interaction between at least one detector and the environment of that detector [(that is, a computer system for implementing a hybrid machine vision model)]”) to optimize performance of a machine vision job, the system comprising:
[(a)] a computing device (Gladish ¶ 0135 teaches “he data processing apparatus 300 is a personal computer, server, cloud-based server, or embedded computer [(that is, computing device)]”) configured to train a machine vision job (Gladish ¶ 0013 teaches “images chosen as training data according to the second visual parameter specification may be useful for training a computer vision model [(that is, training a machine vision job)]”), the computing device including:
one or more processors (Gladisch ¶ 0135 teaches “the data processing apparatus 300 is a personal computer, server, cloud-based server, or embedded computer. It is not essential that the processing occurs on one physical processor [(that is, one or more processors)]”); and
a non-transitory computer-readable memory coupled to the machine vision camera and the one or more processors (Gladisch ¶ 0138 teaches ”a computer readable medium comprising at least one of the computer programs according to the fifth aspect [(that is, a non-transitory computer-readable memory coupled to the machine vision camera and the one or more processors)]”), the memory storing instructions thereon that, when executed by the one or more processors, cause the one or more processors to:
[(a.1)] (a) receive a set of training images (Gladisch ¶ 0013 teaches “images chosen as training data according to the second visual parameter specification may be useful for training a computer vision model [(that is, receive a set of training images )]”),
[(a.2)] (b) generate, by the one or more machine vision tools, prediction values corresponding to an analysis of each training image of the set of training images (Gladisch ¶ 0066 teaches “obtaining 104 a first visual parameter specification comprising at least one initial visual parameter set, wherein an item of visual data [(that is, each training image)] provided based on the extent of the at least one visual parameter set is capable of affecting [(that is, “based on the extent of . . . affecting” is generate . . . prediction values corresponding to an analysis)] a classification or regression performance of the computer vision model [(that is, generating, by the one or more machine vision tools, prediction values corresponding to an analysis of each training image of the set of training images)]”),
[(a.3)] (c) input the prediction values into a machine learning (ML) model configured to receive the prediction values and output a change value corresponding to one or more parameters of the machine vision job (Gladisch ¶ 0085 & Fig. 2, teaches providing “visual parameters [that] are oversampled at regions that are suspected to define performance corners of the computer vision model 16 [Examiner annotations in dashed-line text boxes]:”
PNG
media_image1.png
704
1245
media_image1.png
Greyscale
Gladisch ¶ 0091 teaches “[t]he result is a plurality of performance scores according to the sampled values of the visual parameter specification [(that is, inputting the prediction values into a machine learning (ML) model configured to receive prediction values)]”; Gladisch ¶¶ 0092-93 teaches “obtaining a plurality of performance scores further comprises generating, using the computer vision model, a plurality of predictions of elements of observed scenes in the subset of items of visual data. . . to thus obtain the plurality of performance scores [(that is, “performance scores” is output a change value corresponding to one or more parameters of the machine vision job)]”),
[(a.3.1)] the change value representing an adjustment to the one or more parameters of the machine vision job to eliminate an incorrect outcome of the analysis (Gladisch ¶ 0099 teaches “refining step 45 uses the results of the global sensitivity analysis 19 [(that is, the “result” is the change value)] to modify at least one initial visual parameter of the visual parameter specification [(that is, representing an adjustment to the one or more parameters of the machine vision job to eliminate an incorrect outcome of the analysis)], to thus yield a second visual parameter specification”),
[(a.4)] (d) adjust the machine vision job based on the change value (Gladisch ¶ 0099 teaches “refining step 45 uses the results of the global sensitivity analysis 19 [(that is, the “result” is the change value)] to modify at least one initial visual parameter of the visual parameter specification, to thus yield a second visual parameter specification [(that is, “yield a second visual parameter specification” is the change value representing an adjustment to the one or more parameters of the machine vision job to eliminate an incorrect outcome of the analysis)]”),
[(a.5)] (e) iteratively perform steps (a)-(e) until the ML model determines that the prediction values satisfy a prediction threshold (Gladisch ¶ 0098 teaches “The testing step 17 and the global sensitivity analysis 19 and/or retraining the computer vision model 16 can be repeated. Optionally, the performance scores and variances of the performance score are tracked during such training iterations [(that is, iteratively performing steps (a)- (e) until the ML model determines that the prediction values satisfy a prediction threshold)]. The training iterations are stopped when the variances of the performance score appear to have settled (stopped changing significantly) [(that is, “settled” is the prediction values satisfy a prediction threshold)]”), and
* * *
Though Gladisch teaches improving the visual parameter specification according to a sensitivity analysis of a computer vision model used in object detection and/or recognition, Gladisch, however, does not explicitly teach [a machine vision camera] . . . to produce an inspection result, Gladisch also does not explicitly teach -
* * *
and [(a.6)] transmit the machine vision job to the machine vision camera for execution on the run-time image
[(b)] a machine vision camera configured to:
[(b.1)] receive the trained machine vision job;
[(b.2)] capture a run-time image of a target object;
[(b.3)] execute the trained machine vision job on the run-time image;
[(b.4)] produce, via the trained machine vision job, an inspection result.
But Noone teaches [a machine vision camera] . . . to produce an inspection result. (Noone ¶ 0274 teaches “the use of a machine learning algorithm to analyze in-process or post-build inspection data for the purpose of identifying object defects [(that is, produce an inspection result)]”).
Noone also teaches –
* * *
and [(a.6)] transmit the machine vision job to the machine vision camera for execution on the run-time image (Noone ¶ 0043 teaches “a manufacturing apparatus will be configured to send and/or receive [(that is, “send” is transmit)] process monitoring data, object property or inspection data, and/or process control data [(that is, “process control data” is a machine vision job)] to/from one or more processors that may be co-located with the manufacturing apparatus or located remotely; Noone ¶ 0048 teaches “the term ‘data stream’ refers to a continuous or discontinuous series or sequence of analog or digitally-encoded signals (e.g., voltage signals, current signals, image data comprising spatially-encoded light intensity and/or wavelength data, etc.) used to transmit or receive information [(that is, transmit the machine vision job to the machine vision camera)]”) for execution on the run-time image (Noone ¶ 0051 teaches “the term “real-time” refers to the rate at which sensor data is acquired, processed, and/or used in a feedback loop with a machine learning algorithm to update a classification of object defects or to update a set or sequence of process control parameters in response to changes in one or more input process data streams comprising process simulation data, process characterization data, in-process inspection data, post-build inspection data, or any combination thereof [(that is, for execution on the run-time image)]”;
[Examiner notes that in the execution of processes, the broadest reasonable interpretation of the term “run-time” is synonymous to the term real-time of the cited art of Noone, which is not inconsistent with the Applicant’s Specification (MPEP § 2111)]).
[(b)] a machine vision camera (Noone, Fig. 1, teaches a single integrated system [Examiner annotations in dashed-line text boxes]:
PNG
media_image2.png
719
1067
media_image2.png
Greyscale
Noone ¶ 0005 teaches “the method is implemented using . . . a single integrated system [(that is, machine vision camera)] comprising a manufacturing apparatus, a sensor, and a processor”; Noone ¶ 0007 teaches “the processor is further programmed to provide a predicted optimal set of one or more starting manufacturing process control parameters that is derived using the machine learning algorithm”; Noone ¶ 0212 teaches “[m]achine vision systems provide imaging-based automatic inspection and analysis for a variety of industrial inspection, process control, and robot guidance applications, and may comprise any of a variety of image sensors or cameras, light sources or illumination systems, and additional imaging optical components, as well as processors and image processing software [(that is, the machine vision camera)]”) configured to:
[(b.1)] receive the trained machine vision job (Noone ¶ 0053 teaches “automated object defect classification and real-time adaptive control of manufacturing processes [(that is, receive the trained machine vision job)] may be used with any of a variety of manufacturing processes known to those of skill in the art. Examples include, but are not limited to, additive manufacturing processes, joining processes, forming processes, composite manufacturing processes, subtractive manufacturing processes, surface preparation processes, inspection processes, assembly processes, or any combination thereof”; see Noone ¶¶ 0054-0151 regarding example manufacturing processes);
[(b.2)] capture a run-time image of a target object (Noone ¶ 0008 teaches “automated classification of manufactured object defects (i.e., in real time as the object is being fabricated) [(that is, being in “real-time” is a run-time)], the methods comprising: . . . providing one or more sensors, wherein the one or more sensors provide real-time data for one or more manufactured object properties; Noone ¶ 0197 teaches ”[a]ny of a variety of process monitoring tools known to those of skill in the art may be used including, but not limited to, . . . image sensors and machine vision systems, . . . . In some embodiments, the process characterization sensors may comprise one or more sensors, cameras, or imaging systems that detect electromagnetic radiation that is reflected, scattered, absorbed, transmitted, or emitted by the object [(that is, capture a run-time image of a target object object)]”
[Examiner notes that in the execution of processes, the broadest reasonable interpretation of the term “run-time” is synonymous to the term real-time of the cited art of Noone, which is not inconsistent with the Applicant’s Specification (MPEP § 2111)]);
[(b.3)] execute the trained machine vision job on the run-time image (Noone ¶ 0212 teaches “[m]achine vision systems provide imaging-based automatic inspection and analysis for a variety of industrial inspection, process control, and robot guidance applications, and may comprise any of a variety of image sensors or cameras, light sources or illumination systems, and additional imaging optical components, as well as processors and image processing software”; Noone ¶ 0246 teaches “support vector machines are supervised learning algorithms used for classification and regression analysis of object defect classification data or manufacturing process control [(that is, execute the trained machine vision job on the run-time image)]”);
[(b.4)] produce, via the trained machine vision job, an inspection result (Noone ¶ 0234 teaches “the part is monitored in real-time using an automated object defect classification system as disclosed herein. Once the current build state of the part has been determined, a reinforcement learning algorithm uses the current state information, sj, and the model developed using past training data to predict a proposed action, aj+1, (e.g., a set or sequence of process control parameter adjustments) that will maximize a reward function [(that is, “state information sj” is produce, via the trained machine vision job, an inspection result)]”.
Gladisch and Noone are from the same or similar field of endeavor. Gladisch teaches improving the visual parameter specification according to a sensitivity analysis of a computer vision model. Noone teaches subtraction of a reference data set from the sensor data to increase contrast between normal and defective features of an object.
Thus, it would have been obvious to a person having ordinary skill in the art as of the effective filing date of the Applicant’s invention to modify Gladisch pertaining to sensitivity analysis of a computer vision model with the run-time image analysis of a target object and output an inspection result of Noone.
The motivation to do so is to “make adjustment(s) to one or more process control parameters in order to improve, for example, the dimensional accuracy of the layer, layer surface finish and/or adhesion properties, and/or the overall efficiency of the deposition process.” (Noone ¶ 0210).
Examiner notes that the Applicant’s preamble does not afford patentable weight to the Applicant’s claims because the claim preamble is not “necessary to give life, meaning, and vitality” to the claim. Moreover, because the Applicant’s preamble merely states the purpose or intended use of the invention rather than any distinct definition of any of the claimed invention’s limitations, the preamble is not considered a limitation and is of no significance to claim construction.
Regarding claim 15, Gladisch teaches [a] tangible machine-readable medium comprising instructions for implementing a hybrid machine vision model (Gladisch ¶ 0138 teaches ”a computer readable medium comprising at least one of the computer programs according to the fifth aspect [(that is, a tangible machine-readable medium comprising instructions for implementing a hybrid machine vision model)]”) to optimize performance of a machine vision job, when executed, cause a machine to at least:
(a) receive, at a machine vision job including one or more machine vision tools (Gladisch ¶ 0003 teaches “[c]omputer vision can process inputs from any interaction between at least one detector and the environment of that detector [(that is, a machine vision job)]. The environment may be perceived by the at least one detector as a scene or a succession of scenes. In particular, interaction may result from at least one camera, a multi-camera system, a RADAR system or a LIDAR system;” Gladisch ¶ 0137 teaches that, “[i]n an example, the apparatus 300 is an automotive embedded computer comprised in a vehicle, in which case the automotive embedded computer may be connected to sensors and actuators present in the vehicle. . . . [T]he output interface 340 of the apparatus 300 may interface with one or more of a plurality of brake actuators, throttle actuators, fuel mixture or fuel air mixture actuators, a turbocharger controller, a battery management system, the car lighting system or entertainment system, and the like [(that is, “actuators” are a machine vision job including one or more machine vision tools)]”), a set of training images (Gladisch ¶ 0013 teaches “images chosen as training data according to the second visual parameter specification may be useful for training a computer vision model [(that is, receive . . . a set of training images )]”);
(b) generate, by the one or more machine vision tools, prediction values corresponding to an analysis of each training image of the set of training images (Gladisch ¶ 0066 teaches “obtaining 104 a first visual parameter specification comprising at least one initial visual parameter set, wherein an item of visual data [(that is, each training image)] provided based on the extent of the at least one visual parameter set is capable of affecting [(that is, “based on the extent of . . . affecting” is generate . . . prediction values corresponding to an analysis)] a classification or regression performance of the computer vision model [(that is, generating, by the one or more machine vision tools, prediction values corresponding to an analysis of each training image of the set of training images)]”),
(c) input the prediction values into a machine learning (ML) model configured to receive the prediction values and output a change value corresponding to one or more parameters of the machine vision job (Gladisch ¶ 0085 & Fig. 2, teaches providing “visual parameters [that] are oversampled at regions that are suspected to define performance corners of the computer vision model 16 [Examiner annotations in dashed-line text boxes]:”
PNG
media_image1.png
704
1245
media_image1.png
Greyscale
Gladisch ¶ 0091 teaches “[t]he result is a plurality of performance scores according to the sampled values of the visual parameter specification [(that is, inputting the prediction values into a machine learning (ML) model configured to receive prediction values)]”; Gladisch ¶¶ 0092-93 teaches “obtaining a plurality of performance scores further comprises generating, using the computer vision model, a plurality of predictions of elements of observed scenes in the subset of items of visual data. . . to thus obtain the plurality of performance scores [(that is, “performance scores” is output a change value corresponding to one or more parameters of the machine vision job)]”),
[(c.1)] the change value representing an adjustment to the one or more parameters of the machine vision job to eliminate an incorrect outcome of the analysis (Gladisch ¶ 0099 teaches “refining step 45 uses the results of the global sensitivity analysis 19 [(that is, the “result” is the change value)] to modify at least one initial visual parameter of the visual parameter specification [(that is, representing an adjustment to the one or more parameters of the machine vision job to eliminate an incorrect outcome of the analysis)], to thus yield a second visual parameter specification”),
(d) adjust the machine vision job based on the change value (Gladisch ¶ 0099 teaches “refining step 45 uses the results of the global sensitivity analysis 19 [(that is, the “result” is the change value)] to modify at least one initial visual parameter of the visual parameter specification, to thus yield a second visual parameter specification [(that is, “yield a second visual parameter specification” is the adjust the machine vision job based on the change value)]”),
(e) iteratively perform steps (a)-(e) until the ML model determines that the prediction values satisfy a prediction threshold (Gladisch ¶ 0098 teaches “The testing step 17 and the global sensitivity analysis 19 and/or retraining the computer vision model 16 can be repeated. Optionally, the performance scores and variances of the performance score are tracked during such training iterations [(that is, iteratively performing steps (a)- (e) until the ML model determines that the prediction values satisfy a prediction threshold)]. The training iterations are stopped when the variances of the performance score appear to have settled (stopped changing significantly) [(that is, “settled” is the prediction values satisfy a prediction threshold)]”), and
* * *
Though Gladisch teaches improving the visual parameter specification according to a sensitivity analysis of a computer vision model used in object detection and/or recognition, Gladisch, however, does not explicitly teach -
* * *
and [(f)] transmit the machine vision job to a machine vision camera for execution to analyze a run-time image of a target object without the ML model and output an inspection result.
But Noone teaches –
* * *
and [(f)] transmit the machine vision job without the ML model to a machine vision camera (Noone ¶ 0043 teaches “a manufacturing apparatus will be configured to send and/or receive [(that is, “send” is transmit)] process monitoring data, object property or inspection data, and/or process control data [(that is, “process control data” is a machine vision job)] to/from one or more processors that may be co-located with the manufacturing apparatus or located remotely; Noone ¶ 0048 teaches “the term ‘data stream’ refers to a continuous or discontinuous series or sequence of analog or digitally-encoded signals (e.g., voltage signals, current signals, image data comprising spatially-encoded light intensity and/or wavelength data, etc.) used to transmit or receive information [(that is, transmit the machine vision job . . . to a machine vision camera)]”; Noone ¶ 0248 teaches “the automated object defect classification and additive manufacturing process control methods and systems of the present disclosure may employ an ANN architecture [(that is, the ML model)] wherein the training data set is continuously updated with real-time object classification data or real-time manufacturing process control and monitoring data from a single local manufacturing apparatus or system, from a plurality of local manufacturing apparatuses or systems, or from a plurality of geographically distributed manufacturing apparatuses or systems”; Noone ¶ 0007 teaches “distributed system modules that share training data and real-time process characterization data or in-process inspection data via a local area network (LAN), an intranet, an extranet, or an internet [(that is, in a “distributed system” and “shared and exchanged” is transmit the machine vision job without the ML model)]”) for execution to analyze a run-time image of a target object and output an inspection result (Noone ¶ 0051 teaches “the term “real-time” refers to the rate at which sensor data is acquired, processed, and/or used in a feedback loop with a machine learning algorithm to update a classification of object defects [(that is, a target object )] or to update a set or sequence of process control parameters in response to changes in one or more input process data streams [(that is, output an inspection result)] comprising process simulation data, process characterization data, in-process inspection data, post-build inspection data, or any combination thereof [(that is, for execution to analyze a run-time image of a target object and output an inspection result)]”;
[Examiner notes that in the execution of processes, the broadest reasonable interpretation of the term “run-time” is synonymous to the term real-time of the cited art of Noone, which is not inconsistent with the Applicant’s Specification (MPEP § 2111)]).
Gladisch and Noone are from the same or similar field of endeavor. Gladisch teaches improving the visual parameter specification according to a sensitivity analysis of a computer vision model. Noone teaches subtraction of a reference data set from the sensor data to increase contrast between normal and defective features of an object.
Thus, it would have been obvious to a person having ordinary skill in the art as of the effective filing date of the Applicant’s invention to modify Gladisch pertaining to sensitivity analysis of a computer vision model with the run-time image analysis of a target object and output an inspection result of Noone.
The motivation to do so is to “make adjustment(s) to one or more process control parameters in order to improve, for example, the dimensional accuracy of the layer, layer surface finish and/or adhesion properties, and/or the overall efficiency of the deposition process.” (Noone ¶ 0210).
Examiner notes that the Applicant’s preamble does not afford patentable weight to the Applicant’s claims because the claim preamble is not “necessary to give life, meaning, and vitality” to the claim. Moreover, because the Applicant’s preamble merely states the purpose or intended use of the invention rather than any distinct definition of any of the claimed invention’s limitations, the preamble is not considered a limitation and is of no significance to claim construction.
Regarding claims 2, 9, and 16, the combination of Gladisch and Noone teaches all of the limitations of claims 1, 8, and 15, respectively, as described above in detail.
Though Gladisch teaches a computer vision systems applied to the automotive or robotic vehicle field, Gladisch, however, does not explicitly teach -
wherein each of the one or more machine vision tools includes one or more parameter values, and adjusting the machine vision job based on the change value further comprises:
adjusting a first parameter value of the one or more parameter values for a first machine vision tool of the one or more machine vision tools.
Noone teaches -
wherein
each of the one or more machine vision tools includes one or more parameter values (Noone ¶ 0055 teaches that in a chemical vapor deposition process, “[e]xamples of process control parameters that may be subject to control by the methods and systems disclosed herein include, but are not limited to, gas influx rate, vacuum level, temperature, and any combination thereof [(that is, each of the one or more machine vision tools includes one or more parameter values)]”), and
adjusting the machine vision job based on the change value further comprises:
adjusting a first parameter value of the one or more parameter values for a first machine vision tool of the one or more machine vision tools (Noone ¶ 0004 teaches "wherein the machine learning algorithm provides output values to adjust one or more manufacturing process control parameters in real-time [(that is, adjusting a first parameter value of the one or more parameter values for first machine vision tool of the one or more machine vision tools)]"; Noone ¶ 0212 teaches "[m]achine vision systems provide imaging-based automatic inspection and analysis for a variety of Industrial inspection, process control"; Noone ¶ 0040 teaches "the disclosed methods for automated classification of object defects and adaptive real-time control may be implemented using components, e.g., computer numerical control (CNC) milling machines, lathes, additive manufacturing and/or welding apparatus, process control monitors or sensors, machine vision systems, and/or post-build Inspection tools, which are co-localized In a specific workspace and which have been Integrated to form stand-alone, self-contained systems").
Gladisch and Noone are from the same or similar field of endeavor. Gladisch teaches improving the visual parameter specification according to a sensitivity analysis of a computer vision model in relation to actuators. Noone teaches to adjust one or more manufacturing process control parameters via a imaging-based automatic inspection device.
Thus, it would have been obvious to a person having ordinary skill in the art as of the effective filing date of the Applicant’s invention to modify Gladisch pertaining visual parameter specification improvements via a computer vision model with the adjustment of manufacturing process control parameters via an imaging-based automatic inspection device of Noone.
The motivation to do so is to “make adjustment(s) to one or more process control parameters in order to improve, for example, the dimensional accuracy of the layer, layer surface finish and/or adhesion properties, and/or the overall efficiency of the deposition process.” (Noone ¶ 0210).
Regarding claims 3, 10, and 17, the combination of Gladisch and Noone teaches all of the limitations of claims 1, 8, and 15, respectively, as described above in detail.
Noone teaches –
wherein
the one or more machine vision tools includes at least two machine vision tools (Noone ¶ 0043 teaches “the term “manufacturing apparatus” may refer either to a stand-alone apparatus or machine (e.g., a stand-alone CNC milling machine, lathe, free form deposition system, welding station, manufacturing workstation, etc.) or a cluster of two or more of the same or dissimilar apparatuses or machines [(that is, the one or more machine vision tools includes at least two machine vision tools)]. . . . In some cases, the manufacturing apparatus (stand-alone or clustered) may optionally include one or more process monitoring and/or object property monitoring sensors or tools [(that is, machine vision tools)]. Typically, a manufacturing apparatus will be configured to send and/or receive process monitoring data, object property or inspection data, and/or process control data to/from one or more processors that may be co-located with the manufacturing apparatus or located remotely”), and
adjusting the machine vision job based on the change value includes adjusting an execution order of the at least two machine vision tools within the machine vision job (Noone ¶ 0234 teaches "[t]hus the learned model may be used to determine a sequence of actions [(that is, execution order)] that optimizes the sum (or weighted sum) of reward values for the next N states"; Noone ¶ 0037 teaches "in-process inspection data (e.g., automated defect classification data) may be used by the machine learning algorithm to determine a set or sequence of process control parameter adjustments that will implement a corrective action, e.g., to adjust a layer dimension or thickness in an additive manufacturing process, so as to correct the defect when first detected [(that is, [adjusting] . . . includes adjusting an execution order of the at least two machine vision tools within the machine vision job)]”).
Regarding claims 4, 11, and 18, the combination of Gladisch and Noone teaches all of the limitations of claims 3, 10, and 15, respectively, as described above in detail.
Noone teaches -
wherein the at least two machine vision tools include at least one of:
(i) an edge detection tool (Noone ¶ 00252 teaches “In some embodiments, specific computer vision algorithms comprise through lines. In some embodiments, computer vision algorithms comprise canny edge detectors [(that is, an edge detection tool)]”),
(ii) a pattern matching tool (Noone ¶ 0217 teaches “The approach is based on the use of a machine learning algorithm for detection and classification of defects [(that is, to “classify” is a pattern matching tool)]”),
(iii) a segmentation tool,
(iv) a thresholding tool,
(v) a barcode decoding tool,
(vi) an optical character recognition tool,
(vii) an object tracking tool,
(viii) an object detection tool,
(ix) a color analysis algorithm, or
(x) an image filtering tool (Noone ¶ 0213 teaches "FIG. 78 shows the processed image after denoising, filtering, and edge detection algorithms have been applied [(that is, an image filtering tool )]").
Regarding claims 5 and 12, the combination of Gladisch and Noone teaches all of the limitations of claims 1 and 8, respectively, as described above in detail.
Though Gladisch teaches where training iterations are stopped when variances of a performance score appear to have settled, Gladisch, however, does not explicitly teach –
wherein the ML model uses a cost function to determine whether or not the prediction values satisfy the prediction threshold.
Noone teaches -
wherein the ML model uses a cost function to determine whether or not the prediction values satisfy the prediction threshold (Noone, Fig. 8, teaches “an action prediction—reward loop for a reinforcement learning algorithm [Examiner annotations in dashed-line text boxes]:”
PNG
media_image3.png
509
572
media_image3.png
Greyscale
Noone ¶ 0233 teaches "may be configured to adjust the process control parameters in real-time as necessary to maximize a reward function (or to minimize a loss function) in order to optimize the deposition process. As used herein, a reward function (or conversely, a loss function (sometimes also referred to as a cost function or error function)) . . . . [T]he machine learning algorithm used to run the process control method will seek to optimize the reward function (or minimize the loss function) by (i) identifying the current ‘state’ of the part under fabrication (e.g., based on the real-time stream of process characterization data supplied by one or more sensors), (ii) comparing the current “state” to the design target (or reference “state”), and (iii) adjusting one or more process control parameters in order to minimize the difference [(that is, minimize the difference)] between the two states (e.g., based on past “learning” provided by the training data set) [(that is, the “minimize the difference” is whether or not the prediction values satisfy the prediction threshold)]”).
Gladisch and Noone are from the same or similar field of endeavor. Gladisch teaches a threshold by which where training iterations are stopped when variances of a performance score appear to have settled. Noone teaches adjusting process control parameters to maximize a reward function, which is also sometimes referred to as a cost function.
Thus, it would have been obvious to a person having ordinary skill in the art as of the effective filing date of the Applicant’s invention to modify Gladisch pertaining to a threshold for a performance score with the cost-function threshold of Noone.
The motivation to do so is to “make adjustment(s) to one or more process control parameters in order to improve, for example, the dimensional accuracy of the layer, layer surface finish and/or adhesion properties, and/or the overall efficiency of the deposition process.” (Noone ¶ 0210).
Regarding claims 6, 13, and 19, the combination of Gladisch and Noone teaches all of the limitations of claims 1, 8, and 15, respectively, as described above in detail.
Noone teaches -
wherein the set of training images includes image labels indicating an inspection result corresponding to each training image, and
inputting the prediction values into the ML model further comprises:
inputting the prediction values and the image labels into the ML model in order to output the change value (Noone ¶ 0240 teaches “Supervised learning algorithms: In the context of the present disclosure, supervised learning algorithms are algorithms that rely on the use of a set of labeled training data to infer the relationship between a set of one or more defects identified for a given object [(that is, “identified” is image labels indicating an inspection result corresponding to each training image)] and a classification of the object according to a specified set of quality criteria [(that is, the prediction values)] . . . The training data comprises a set of paired training examples [(that is, “paired” is inputting the prediction values and the image labels into the ML model)], e.g., where each example comprises a set of defects detected for a given object [(that is, image labels indicting an inspection result)] and the resultant classification of the given object [(that is, prediction values)], or where each example comprises a set of process control parameters that were used in a fabrication or assembly process that is paired with the known outcome of the fabrication or assembly process”; Noone ¶ 0004 teaches "the machine learning algorithm provides output values to adjust one or more manufacturing process control parameters in real-time [(that is, in order to output the change value)]";).
Regarding claims 7, 14, and 20, the combination of Gladisch and Noone teaches all of the limitations of claims 1, 8, and 15, respectively, as described above in detail.
Noone teaches -
wherein the machine vision camera executes the trained machine vision job to analyze the run-time image without inputting run-time image data into the ML model (Noone ¶ 0035 teaches “For example, process simulation tools such as finite element analysis (FEA) may be used to simulate the process for fabricating an object or a specific portion thereof, e.g., a feature, from any of a variety of fabrication materials as a function of a specified set of process control parameters [(that is, under “simulation” is without inputting run-time image data into the ML model)]. In some embodiments, process simulation tools may be used to predict an optimal starting set or sequence of process control parameters for fabricating a specified object or object feature [(that is, wherein the machine vision camera executes the machine vision job to analyze the run-time image without inputting run-time image data into the ML model)]”), and
the inspection result corresponds to whether or not the run-time image data satisfies a set of inspection criteria (Noone ¶ 0274 teaches "[t]he methods comprise the use of a machine learning algorithm to analyze in-process or post-build inspection data for the purpose of identifying object defects and classifying them according to a specified set of fabrication quality criteria [(that is, a set of inspection criteria)], and in some embodiments, further provide input data for real-time adaptive process control [(that is, the inspection result corresponds to whether or not the run-time image data satisfies a set of inspection criteria)]").
Response to Arguments
10. Examiner has fully considered Applicant’s arguments, and responds below accordingly.
Section 101
11. Applicant submits that, “as noted in specification, the trained machine vision job can be executed by the machine vision camera, where the trained machine vision job can specify parameters and/or settings of the camera itself such that an operation of the camera can be improved.” (Response at p. 9 (quoting Specification ¶ 0051)).
Applicant submits that “[u]nder Step 1 of the Alice framework, the claims are analyzed to determine if they are "directed to" a patent-ineligible concept. While the claim involves a machine learning model, it is not "directed to" an abstract idea itself Instead, it is directed to a specific improvement in the functioning of a machine vision system.” (Response at p. 9).
Applicant also submits that “[t]he focus of amended claim 1 is precisely such an improvement [as set out by Enfish]: optimizing the performance of a machine vision system by creating a specific, iterative training process for generating a trained machine vision job and subsequently deploying the trained machine vision job, which is used by a machine vision camera, e.g., to set operational parameters/settings, and e.g., to control a manner in which images captured by the camera are processed. As such, the claim does not merely use a computer to perform an abstract task but improves the functionality of the machine vision system itself.” (Response at pp. 9-10).
Under Step 2A Prong Two, Applicant submits that “the specification clearly describes the problem faced by prior art machine vision systems, namely, machine vision ("MV") systems utilizing machine learning ("ML") increase computational resources and time required to operate, and MV systems not utilizing ML require significantly increased setup and maintenance time. (Response at p. 10 (quoting Specification ¶¶ 0001 & 0029)).
The technical solution pointed to by the Applicant is that:
the techniques of the present disclosure improve over conventional machine vision systems at least by utilizing a ML model to train a machine vision job while offline. Such offline training ensures that the online operation of the machine vision job does not require the cumbersome computational load of conventional ML-based machine vision systems, and avoids the substantial upfront configuration cost and the persistent manual maintenance cost of conventional non-ML-based machine vision systems.
(Response at pp. 11 (Specification ¶¶ 0030, 0031)).
Applicant submits that “the specification clearly describes, and the claims clearly provide for, a technical improvement over the prior art by utilizing a hybrid [machine vision] approach - ML algorithms are used to adjust the parameters of a traditional MV job, however, the ML algorithms themselves are not used to perform the actual MV job, thereby improving efficiencies of the overall system.” (Response at p. 12).
Examiner Response:
Under Step 2A Prong Two, the rejection identifies any additional elements recited in the claim beyond the identified judicial exception (i.e., abstract idea); and evaluate the integration of the judicial exception into a practical application by explaining that the claim as a whole, looking at the additional elements individually and in combination, does not integrate the judicial exception into a practical application using the considerations set forth in MPEP §§ 2106.04(d), 2106.05(a)-(c) and (e)-(h).
“Integration” may be based on the improvements in the functioning of a computer or an improvement to any other technology or technical field. (MPEP § 2106.04(d)(1)). The evaluation requires, [i]n sum, that (1) the specification should be evaluated to determine if the disclosure provides sufficient details such that one of ordinary skill in the art would recognize the claimed invention as providing an improvement. Next, (2) if the specification sets forth such an improvement, the claim must be evaluated to ensure that the claim itself reflects the disclosed improvement.
By way of example to Desjardins, the MPEP provides under Step 2A Prong Two that “the [Desjardins] specification identified improvements as to how the machine learning model itself operates, including training a machine learning model to learn new tasks while protecting knowledge about previous tasks to overcome the problem of ‘catastrophic forgetting’ encountered in continual learning systems. Importantly, the [appeals review panel (ARP)] evaluated the claims as a whole in discerning at least the limitation ‘adjust the first values of the plurality of parameters to optimize performance of the machine learning model on the second machine learning task while protecting performance of the machine learning model on the first machine learning task’ reflected the improvement disclosed in the specification. Accordingly, the claims as a whole integrated what would otherwise be a judicial exception instead into a practical application at Step 2A Prong Two, and therefore the claims were deemed to be outside any specific, enumerated judicial exception (Step 2A: NO).” (MPEP § 2106.04(d) sub III; see “Advance Notice of Change to the MPEP in light of Ex Parte Desjardins” (05 December 2025) at p. 2)).
Generally, a problem addressed in Applicant’s disclosure is that conventional machine vision systems create a tradeoff. ML-based systems can reduce manual intervention, but they are computationally intensive and may require extra hardware. Non-ML systems are lighter at runtime, but they are harder for field engineers to set up and maintain. The stated need is for a hybrid approach that improves accuracy and efficiency without the runtime burden of full ML inspection. (see Specification ¶ 0001-02).
Exemplar claim 1 recites, inter alia, training a machine vision job, where:
* * *
[(a.3)] (c) inputting the prediction values into a machine learning (ML) model configured to receive prediction values and output a change value corresponding to one or more parameters of the machine vision job,
[(a.3.1)] the change value representing an adjustment to the one or more parameters of the machine vision job to eliminate an incorrect outcome of the analysis;
[(a.4)] (d) adjusting the machine vision job based on the change value;
[(a.5)] (e) iteratively performing steps (a)-(e) until the ML model determines that the prediction values satisfy a prediction threshold;
* * *
(claim 1, lines 8-15). In effect, the training is directed to improve a machine vision job accuracy by the intended result “to eliminate an incorrect outcome of the analysis.” Generally, the claimed methods are not rendered patent eligible by the fact that using existing machine learning technology performs a task previously undertaken by humans with greater speed and efficiency than could previously be achieved. (Recentive Analytics, Inc. v. Fox Corp., 2025 USPQ2d 628 at p.*6 (Fed. Cir. 2025); see MPEP § 2106.05(d)(1)); Specification ¶ 0235 & Fig. 9)).
Accordingly, as set out above in detail, the instant claims are subject-matter ineligible.
Section 103
12. Regarding claims 1-14, Applicant submits that “Gladisch and Noone, when considered alone or in combination fail to disclose, teach, or suggest, inter alia,
[(a)] training a machine vision job by:
* * *
[(a.5)] iteratively performing steps (a)-(e) [of claim 1] until the ML model determines that the prediction values satisfy a prediction threshold; and
[(b)] inspecting a target object by:
[(b.1)] deploying the trained machine vision job on the machine vision camera;
[(b.2)] imaging the target object with the machine vision camera to capture a run-time image of the target object;
[(b.3)] executing, on the machine vision camera, the trained machine vision job to analyze a run-time image of a target object; and
[(b.4)] outputting, by the trained machine vision job, an inspection result,
as recited by claim 1.” (Response at p. 13 (claim 1, lines 3, 16-22) (emphasis added by Examiner reflecting modified language)).
Examiner Response:
Examiner respectfully submits that Noone teaches the features of Applicant’s claims as set out above in detail. (see Noone ¶ 0005, 0007 & 0212 (“image visions systems provide image-based automatic inspection and analysis for a variety of industrial inspection”)).
Also, the rejections hereinabove clearly sets forth which claim limitations are taught by each of the prior art references, and the reason why it would be obvious to a person having ordinary skill in the art as of the effective filing date of the Applicant's invention to combine their teachings, and Applicant has not explained why the cited prior art references cannot be combined in the manner set forth in the rejection.
13. With respect to claim 15, Applicant submits that “Gladisch and Noone, when considered alone or in combination fail to disclose, teach, or suggest, inter alia,
transmit the machine vision job to a machine vision camera for execution to analyze a run-time image of a target object without the ML model and output an inspection result,
as recited by claim 15.” (Response at p. 14 (claim 15, lines 15-16)).
Examiner Response:
Examiner respectfully submits that Noone teaches the features of “transmit the machine vision job to the machine vision camera for execution on the run-time image” of Applicant’s claims (see Noone ¶ 0051 (“real-time” refers to the rate at which sensor data is acquired, processed, and/or used in a feedback loop”).
Examiner notes that in the execution of processes, the broadest reasonable interpretation of the term “run-time” is synonymous to the term real-time of the cited art of Noone, which is not inconsistent with the Applicant’s Specification (MPEP § 2111).
Also, the rejections hereinabove clearly sets forth which claim limitations are taught by each of the prior art references, and the reason why it would be obvious to a person having ordinary skill in the art as of the effective filing date of the Applicant's invention to combine their teachings, and Applicant has not explained why the cited prior art references cannot be combined in the manner set forth in the rejection.
Conclusion
14. The prior art made of record and not relied upon is considered pertinent to Applicant's disclosure:
(US Published Application 20220172100 to Balasubramanian et al.) teaches To overcome the issues with manual inspection, some companies have applied automated image analysis—a technology known as machine vision—to detect anomalies. These expensive, purpose-built systems of cameras and computers must be calibrated for lighting and perspective with hard-coded rules about what is and isn't a defect to support a single, specialized task and environment.
(Benbarrad et al., “Intelligent Machine Vision Model for Defective Product Inspection Based on Machine Learning,” Journal of Sensor & Actuator Networks (2021)) teaches a proposed machine vision model in this paper combines the identification of defective products and the continuous improvement of manufacturing processes by predicting the most suitable parameters of production processes to obtain a defect-free item. The suggested model exploits all generated data by various integrated technologies in the manufacturing chain, thus meeting the requirements of quality management in the context of Industry 4.0, based on predictive analysis to identify patterns in data and suggest corrective actions to ensure product quality.
15. Any inquiry concerning this communication or earlier communications from the Examiner should be directed to KEVIN L. SMITH whose telephone number is (571) 272-5964. Normally, the Examiner is available on Monday-Thursday 0730-1730.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, Applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the Examiner by telephone are unsuccessful, the Examiner’s supervisor, KAKALI CHAKI can be reached on 571-272-3719. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of an application may be obtained from the Patent Application Information Retrieval (PAIR) system. Status information for published applications may be obtained from either Private PAIR or Public PAIR. Status information for unpublished applications is available through Private PAIR only. For more information about the PAIR system, see http://pair-direct.uspto.gov. Should you have questions on access to the Private PAIR system, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative or access to the automated information system, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/K.L.S./
Examiner, Art Unit 2122
/KAKALI CHAKI/Supervisory Patent Examiner, Art Unit 2122
1 References to the limitations are provided for the limited purpose of aiding in the subject-matter eligibility evaluation under the Office guidance and not for the purpose of oversimplifying the claims.
Prosecution Insights