DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Status of Claims
This Office Action is responsive to communication filed on 9/2/2025.
Claims 1, 3 and 10-20 are amended.
Claims 1-20 are pending and presented for examination.
Response to Arguments
Applicant’s arguments with respect to the amended claim(s) 1, 3-10, 12-15 and 17-20 have been considered but are moot because the new ground of rejection does not rely on any reference applied in the prior rejection of record for any teaching or matter specifically challenged in the argument.
Claim Rejections - 35 USC § 112
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.
The following is a quotation of 35 U.S.C. 112 (pre-AIA ), second paragraph:
The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the applicant regards as his invention.
Claims 1-20 are rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor (or for applications subject to pre-AIA 35 U.S.C. 112, the applicant), regards as the invention.
Regarding claim 1
The first limitation of claim 1 recites “registering an image of a product printed by nozzles of the inkjet printing system to generate a corresponding raster file of the image”. The final limitation of claim 1 recites “managing the nozzles of the inkjet printing system […] to generate an affine transformation that aligns the image with the corresponding raster file”.
The Office interprets “registering an image of a product printed […] to generate a corresponding raster file of the image” as using an image detection device (e.g., a camera) to take an image of a product printed to generate a bitmap. The claim concludes with “managing the nozzles […] to generate an affine transformation that aligns the image with the corresponding raster file”. If the raster file is generated as a result of the picture, then the Office is not sure how the picture would not align with the raster file, as the raster file is generated from the picture, thus rendering the claim indefinite.
In the interest of advancing prosecution, the Office will interpret the first limitation of claim 1 as “registering an image of a product printed by nozzles of the inkjet printing system with respect to
Additionally, the final limitation of the claim recites “managing the nozzles of the inkjet printing system […] by applying the neural network (NN) to generate an affine transformation that aligns the image with the corresponding raster file.” It is clear that the neural network is the mechanism by which the affine transformation (which aligns the image with the raster file) is generated. However, the claim fails to recite that the nozzles are managed using the generated affine transformation, thus rending the claim indefinite.
In the interest of advancing prosecution, the Office will interpret the last limitation of claim 1 as “managing the nozzles of the inkjet printing system to apply ink droplets to a substrate forming an image in 2D printing or a product comprising multiple polymer layers deposited one on top of another in 3D printing by applying the neural network (NN) to generate an affine transformation that aligns the image with the corresponding raster file, wherein the nozzles are managed by the affine transformation.”
Claims 2-9 are also rejected due to being dependent on claim 1 and inheriting this deficiency.
Claims 10 and 15 recite this same deficiency. Claim 10 and its dependents 11-14, and claim 15 and its dependents 16-20 are rejected due to the reasons outlined above.
Claim Rejections - 35 USC § 103
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.
Claims 1, 3-10, 12-15 and 17-20 are rejected as being unpatentable over Baker (US20190210052A1) in view of Schultz (US20200307101A1)1.
Regarding claim 1, Baker teaches a method comprising:
registering an image of a product printed by nozzles of the inkjet printing system with respect to a corresponding raster file of the image ([0064]: bitmap; [0073]-[0074]: each array or substrate can have non-uniformities in its position, rotation, scale, skew, or other alignment issues which affect registration of the deposited layer for one or more of the products; imaged data is used by processor to compare actual position of the substrate to expected position; [0153]: image is used to precisely detect fiducial position);
evaluating performance of the nozzles of the inkjet printing system to detect that the image is not aligned with the corresponding raster file ([0153]: detected fiducial parameters (such as position, size, shape, rotation, skew, or associated fiducial reference points) can be compared to expected parameters for such fiducials, to detect error. As noted, any detected error can involve one or more of translational, rotational, scaling or skew error, or a superposition of multiple such errors), and
managing the nozzles of the inkjet printing system to apply ink droplets to a substrate forming an image in 2D printing or a product comprising multiple polymer layers deposited one on top of another in 3D printing by applying an affine transformation that aligns the images with the corresponding raster file ([0074]: imaged data is then used by a processor to compare actual position of the substrate (and its panels) to expected position; dependent on deviation, the print image is adjusted so that printing registers with panel layout information (and any previously-deposited layers) [0153]: Based on detected error, printer control data is built that corrects for any error so that printing will be in the “right place.” As noted at the right side of the figure, based on alignment mark determination, system software corrects for error by operation upon the template. As noted earlier, the template is retrieved, and the instance of this template is then manipulated (rendered) as appropriate to generate nozzle firing decisions as appropriate via the aforementioned error correction process; [0153]: an affine transform can be applied in order to obtain new firing decision; [0061]: printing ink or liquid for example is a polymer).
Baker is not relied on for applying a neural network trained on a plurality of registered images of the printed product and corresponding raster files. Baker is also not relied on for using the neural network to manage the nozzles.
However, Schultz in an analogous art does teach these claim limitations.
Schultz teaches evaluating performance of the nozzles of the inkjet printing system by applying a neural network (NN) trained on a plurality of registered images of the printed product and corresponding files to detect a defect of the inkjet printing system ([0028]-[0030]: one or more processors 104 may further execute the machine-readable instructions to, based on the identified print defect(s), alert the user, abort a print job, and/or adjust operating parameters of the three-dimensional printer 130 […] module 119 may include an artificial intelligence component to train and provide machine-learning capabilities to a neural network as described herein […] image analytics module 118 and the machine-learning module 119 may be communicatively coupled to the communication path 102 and the one or more processors 104 […] the one or more processors 104 may, using at least the image analytics module 118 and/or the machine-learning module 119, process the input signals received from the system 100 modules and/or extract information (e.g., defect detection) from such signals […] to apply and improve upon a model via machine-learning, numerous print jobs may be recorded using the one or more image sensors 120 and used by the machine-learning module 119 to reduce error in the model; [0038]: model object is trained and used for data analytics, includes a collecting of training data sets based on images data placed within the model object), and
managing the nozzles of the inkjet printing system to correct a defect of the inkjet printing system by applying the neural network ([0029]: based on identified defects system may adjust operating parameters of three-dimensional printer; [0050]: depending on the type of defect detected system may automatically adjust operating parameters of the system to fix and/or prevent further defects).
Baker teaches a method of identifying and correcting misalignment between a product printed by a 3D printer and a corresponding bitmap (i.e., raster file). Schultz teaches a method of identifying and preventing further defects between a product printed by a 3D printer by using machine-learning, specifically a neural network. The rationale to combine is provided by Baker in paragraph [0155], in a possible embodiment “system software further detects repeated error that is correlated among substrates, and it can then optionally update the cached template to “learn” the repeatable error and adapt the template to that error […] these and other repeatable errors can be learned by the system and used to reduce per-job error processing.” Furthermore, Baker suggests using a neural network in paragraph [0161], “system effectively “learns” patterns in the errors, for example, based on regression software, a neural net or other adaptive process.” Before the effective filing date of the claimed invention, it would have been obvious to one of ordinary skill in the art to combine Baker and Schultz to arrive at the claimed invention.
Regarding claim 3, Baker in view of Shultz teaches the elements of claim 1 as outlined above. Baker also teaches wherein the registering is carried out by extracting features of the image and/or of the raster file and deriving the affine transformation on at least one thereof with respect to the extract features ([0086]: camera can be used to capture fiducial position, positions particulars are identified, printer control data can be adjusted or rendered using affine transforms).
Regarding claim 4, Baker in view of Shultz teaches the elements of claim 3 as outlined above. Baker also teaches extracting of features and the deriving of the affine transformation are carried out using a trained registration neural network ([0161]: neural net).
Regarding claim 5, Baker in view of Shultz teaches the elements of claim 1 as outlined above. Schultz also teaches wherein the neural network is trained using images of the printed products that are manually analyzed with respect to the corresponding raster files ([0039]: “training data sets may include image data of one or more printed constructs/structures that are annotated by a user to identify defects within the image data”).
Regarding claim 6, Baker in view of Shultz teaches the elements of claim 1 as outlined above. Schultz also teaches wherein the neural network is constructed and trained using a deep learning algorithm ([0030]: “machine-learning module 119 may include artificial intelligence components selected from the group consisting of an artificial intelligence engine, Bayesian inference engine, and a decision-making engine, and may have an adaptive learning engine further comprising a deep neural network-learning engine”).
Regarding claim 7, Baker in view of Shultz teaches the elements of claim 1 as outlined above. Baker also teaches wherein the inkjet printing system is a 2D printing system ([0056]: in specifically contemplated applications, the printer is used to deposit a single layer).
Regarding claim 8, Baker in view of Shultz teaches the elements of claim 1 as outlined above. Baker also teaches wherein the inkjet printing system is a 3d additive manufacturing system (Abstract: manufacturing process uses a printer to deposit liquids for product).
Regarding claim 9, Baker in view of Shultz teaches the elements of claim 1 as outlined above. Baker also teaches wherein at least one of the registering and the evaluating is carried out by at least one computer processor ([0068]: instructions executed cause general purpose machine (e.g., processor or computer) to behave as a special purpose machine).
Regarding claim 10, Baker teaches a non-transitory computer readable storage medium storing instructions thereon ([0054]: various techniques can be embodied as software; [0068]: instructions stored on non-transitory machine-readable media).
The remaining limitations of claim 10 are substantially the same as claim 1 and are rejected due to the reasons outlined above.
Regarding claim 12, Baker in view of Shultz teaches the elements of claim 10 as outlined above. Baker also teaches to extract features of the image and/or of the raster file and derive the affine transformation on at least one thereof with respect to the extracted features, using a trained registration neural network ([0086]: camera can be used to capture fiducial position, positions particulars are identified, printer control data can be adjusted or rendered using affine transforms; [0161]: neural net).
Regarding claim 13, Baker in view of Shultz teaches the elements of claim 10 as outlined above. The remaining limitations of claim 13 are substantially the same as claim 6 and are rejected due to the reasons outlined above.
Regarding claim 14, Baker in view of Shultz teaches the elements of claim 10 as outlined above. Baker also teaches wherein the inkjet printing system is a 2D printing system or a 3D additive manufacturing system (Abstract: manufacturing process uses a printer to deposit liquids for product).
Regarding claim 15, Baker teaches a controller ([0054]: various techniques can be embodied as a computer running such software, in the form of control data; [0068]: instructions executed cause general purpose machine (e.g., processor or computer) to behave as a special purpose machine).
The remaining limitations of claim 15 are substantially the same as claim 1 and are rejected due to the reasons outlined above.
Regarding claim 17, Baker in view of Shultz teaches the elements of claim 15 as outlined above. The remaining limitations of claim 17 are substantially the same as claim 12 and are rejected due to the reasons outlined above.
Regarding claim 18, Baker in view of Shultz teaches the elements of claim 15 as outlined above. The remaining limitations of claim 18 are substantially the same as claim 6 and are rejected due to the reasons outlined above.
Regarding claim 19, Baker in view of Shultz teaches the elements of claim 15 as outlined above. The remaining limitations of claim 19 are substantially the same as claim 7 and are rejected due to the reasons outlined above.
Regarding claim 20, Baker in view of Shultz teaches the elements of claim 15 as outlined above. The remaining limitations of claim 20 are substantially the same as claim 8 and are rejected due to the reasons outlined above.
Claims 2, 11 and 16 are rejected as being unpatentable over Baker (US20190210052A1) in view of Schultz (US20200307101A1), in further view of Cai (US20230004814A1)2.
Regarding claim 2, Baker in view of Shultz teaches the elements of claim 1 as outlined above. Baker in view of Shultz are not relied on for initially detecting and removing invalid session images. However, Cai in an analogous art does teach this claim limitation ([0048]: “a decision is made as to whether the images are plausible”; [0049]: “the image is discarded if the synthesized image is not plausible”). Baker in view of Shultz teaches a method of applying a neural network trained on a plurality of registered images of a printed product and a corresponding raster file. Cai teaches that not all images should be used to train the neural network and that some images should be removed. Before the effective filing date of the claimed invention, it would have been obvious to a person of ordinary skill in the art to improve Baker in view of Shultz with Cai according to known methods to yield predictable results.
Regarding claim 11, Baker in view of Shultz teaches the elements of claim 10 as outlined above. The remaining limitations of claim 11 are substantially the same as claim 2 and are rejected due to the reasons outlined above.
Regarding claim 16, Baker in view of Shultz teaches the elements of claim 15 as outlined above. The remaining limitations of claim 16 are substantially the same as claim 2 and are rejected due to the reasons outlined above.
Conclusion
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to Michael V Farina whose telephone number is (571)272-4982. The examiner can normally be reached Mon-Thu 8:00-6:00 EST.
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, Thomas Lee can be reached at (571) 272-3667. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/M.V.F./Examiner, Art Unit 2115
/THOMAS C LEE/Supervisory Patent Examiner, Art Unit 2115
1 Schultz is a prior art reference cited in the last office action.
2 Cai is a prior art reference cited in the last office action.