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 . Claims 1-20, all the claims pending in the application, are rejected.
Claim Rejections - 35 USC § 112
The following is a quotation of the first paragraph of 35 U.S.C. 112(a):
(a) IN GENERAL.—The specification shall contain a written description of the invention, and of the manner and process of making and using it, in such full, clear, concise, and exact terms as to enable any person skilled in the art to which it pertains, or with which it is most nearly connected, to make and use the same, and shall set forth the best mode contemplated by the inventor or joint inventor of carrying out the invention.
The following is a quotation of the first paragraph of pre-AIA 35 U.S.C. 112:
The specification shall contain a written description of the invention, and of the manner and process of making and using it, in such full, clear, concise, and exact terms as to enable any person skilled in the art to which it pertains, or with which it is most nearly connected, to make and use the same, and shall set forth the best mode contemplated by the inventor of carrying out his invention.
Claims 1-20 are rejected under 35 U.S.C. 112(a) or 35 U.S.C. 112 (pre-AIA ), first paragraph, as failing to comply with the written description requirement. The claim(s) contains subject matter which was not described in the specification in such a way as to reasonably convey to one skilled in the relevant art that the inventor or a joint inventor, or for applications subject to pre-AIA 35 U.S.C. 112, the inventor(s), at the time the application was filed, had possession of the claimed invention.
According to MPEP § 2163(II)(A)(3)(b), “To comply with the written description requirement of 35 U.S.C. 112(a) or pre-AIA 35 U.S.C. 112, first paragraph, or to be entitled to an earlier priority date or filing date under 35 U.S.C. 119, 120, 365, or 386, each claim limitation must be expressly, implicitly, or inherently supported in the originally filed disclosure.”
Since the subject application asserts entitlement to the earlier priority date of U.S. Provisional Application No. 62/955,726 via intervening parent U.S. Non-provisional Application No. 17/123,531, each claim limitation must be supported in the originally filed disclosures of these applications.
Independent claim 1 recites “wherein the texture feature extraction analysis process includes determining distribution of particle sizes within sub-images of the target image…; wherein cumulative distributions are generated to determine the distribution of the particle sizes across the sub-images…and apply a machine learning model to match texture features present in the target coating using…the generated cumulative distributions of the particle sizes across the sub-images”. Independent claim 11 recites nearly identical features. This combination of features does not appear to be supported by the originally filed disclosure of either parent application.
The claim requires two separate distributions: 1) “cumulative distributions of the particle sizes across the sub-images” and 2) a “distribution of the particle sizes across the sub-images”. Importantly, the former informs the latter (“cumulative distributions are generated to determine the distribution”). However, the originally filed disclosure is silent about any sort of relationship or association between two distributions.
Notably, the Examiner notes that the term “cumulative” does not appear at all in the originally filed specification. The term appears in Figs. 23 and 24, but these figures fall well short of support the claim language in which “cumulative distributions are generated to determine the distribution”.
This deficiency raises several questions of inventor possession. For example, how are the cumulative distributions accumulated? How are the cumulative distributions used to generate the distribution? What is the role of the cumulative distributions with respect to the machine learning model that match texture features? Is it different or the same as role of the distribution with respect to the machine learning model?
As best understood, the originally filed disclosure only seems to support a single distribution of particle sizes across the image, and it is that distribution that is input to the machine learning model to determine a match.
For all the foregoing reasons, the Examiner submits that independent claims 1 and 11 contain subject matter which was not described in the specification in such a way as to reasonably convey to one skilled in the relevant art that the inventor or a joint inventor had possession of the claimed invention at the time the application was filed.
Claims 2-10 inherit this issue by virtue of their dependency on claim 1.
Claims 12-20 inherit this issue by virtue of their dependency on claim 11.
Double Patenting
The nonstatutory double patenting rejection is based on a judicially created doctrine grounded in public policy (a policy reflected in the statute) so as to prevent the unjustified or improper timewise extension of the “right to exclude” granted by a patent and to prevent possible harassment by multiple assignees. A nonstatutory double patenting rejection is appropriate where the conflicting claims are not identical, but at least one examined application claim is not patentably distinct from the reference claim(s) because the examined application claim is either anticipated by, or would have been obvious over, the reference claim(s). See, e.g., In re Berg, 140 F.3d 1428, 46 USPQ2d 1226 (Fed. Cir. 1998); In re Goodman, 11 F.3d 1046, 29 USPQ2d 2010 (Fed. Cir. 1993); In re Longi, 759 F.2d 887, 225 USPQ 645 (Fed. Cir. 1985); In re Van Ornum, 686 F.2d 937, 214 USPQ 761 (CCPA 1982); In re Vogel, 422 F.2d 438, 164 USPQ 619 (CCPA 1970); In re Thorington, 418 F.2d 528, 163 USPQ 644 (CCPA 1969).
A timely filed terminal disclaimer in compliance with 37 CFR 1.321(c) or 1.321(d) may be used to overcome an actual or provisional rejection based on nonstatutory double patenting provided the reference application or patent either is shown to be commonly owned with the examined application, or claims an invention made as a result of activities undertaken within the scope of a joint research agreement. See MPEP § 717.02 for applications subject to examination under the first inventor to file provisions of the AIA as explained in MPEP § 2159. See MPEP § 2146 et seq. for applications not subject to examination under the first inventor to file provisions of the AIA . A terminal disclaimer must be signed in compliance with 37 CFR 1.321(b).
The filing of a terminal disclaimer by itself is not a complete reply to a nonstatutory double patenting (NSDP) rejection. A complete reply requires that the terminal disclaimer be accompanied by a reply requesting reconsideration of the prior Office action. Even where the NSDP rejection is provisional the reply must be complete. See MPEP § 804, subsection I.B.1. For a reply to a non-final Office action, see 37 CFR 1.111(a). For a reply to final Office action, see 37 CFR 1.113(c). A request for reconsideration while not provided for in 37 CFR 1.113(c) may be filed after final for consideration. See MPEP §§ 706.07(e) and 714.13.
The USPTO Internet website contains terminal disclaimer forms which may be used. Please visit www.uspto.gov/patent/patents-forms. The actual filing date of the application in which the form is filed determines what form (e.g., PTO/SB/25, PTO/SB/26, PTO/AIA /25, or PTO/AIA /26) should be used. A web-based eTerminal Disclaimer may be filled out completely online using web-screens. An eTerminal Disclaimer that meets all requirements is auto-processed and approved immediately upon submission. For more information about eTerminal Disclaimers, refer to www.uspto.gov/patents/apply/applying-online/eterminal-disclaimer.
Claims 1-20 are rejected on the ground of nonstatutory double patenting as being unpatentable over claims 1-18 of U.S. Patent No. 12,100,171 (hereinafter “the ‘171 patent”) in view of U.S. Patent Application Publication No. 2022/0107222 to Bischoff (hereinafter “Bischoff”).
As to independent claim 1, claim 1 of the ‘171 patent requires a system for matching texture of a target coating comprising: a storage device for storing instructions; one or more data processors configured to execute instructions to (“A system for matching texture of a target coating comprising: a storage device for storing instructions; one or more data processors configured to execute instructions to:”): receive a target image of the target coating, wherein the target image comprises target image data (“receive a target image of the target coating, wherein the target image comprises target image data”); apply a texture feature extraction analysis process to the target image data to determine target image texture features, wherein the texture feature extraction analysis process includes determining distribution of particle sizes within sub-images of the target image, wherein a data spread statistical measure and a center statistical measure are determined to indicate the distribution of particle sizes within the sub-images (“apply a texture feature extraction analysis process to the target image data to determine target image texture features, wherein the texture feature extraction analysis process includes determining distribution of particle sizes within sub-images of the target image, wherein a data spread statistical measure and a center statistical measure are determined to indicate the distribution of particle sizes”); determine target image texture features for the sub-images, and apply a machine learning model to match texture features present in the target coating using the determined target image texture features (“determine target image texture features for the sub-images, wherein a sub-image includes different particles, and apply a machine learning model to match texture features present in the target coating using the determined target image texture features”).
The claims of the ‘171 patent do not require wherein cumulative distributions are generated to determine the distribution of the particle sizes across the sub-images or that the matching of the features present in the target coating is performed using the generated cumulative distributions of the particle sizes across the sub-images.
Bischoff, like the claims of the ‘171 patent, is directed to identifying a formulation for a coating in an image by extracting features therein for comparison with known coating formulations to identify a best match (Abstract and [0011, 0036-0037, 0070-0071]). Similar to the claims of the ‘171 patent, Bischoff contemplates an image segmentation procedure prior to the feature extraction process. Specifically, Bischoff discloses that the images is segmented on the basis of contiguous areas, and the segments are handed over for blob detection in which regions within the image that differ from the surrounding regions in particular qualities are identified ([0101-0104]). Within the detected blobs, individual sparkle points are recognized, and “at least one size feature can then be determined” for each sparkle point ([0105]). The “determined values of the respective size features of all the sparkle points are then…evaluated statistically” so that “sparkle points having values of similar magnitude for the size features considered can be grouped together” and the “average area…, average diameter…, standard deviation of the areas…, [and] standard deviation of the diameters” are determined for each group, thereby “produc[ing] a size distribution 18 of the sparkle points” ([0106-0115]). Finally, the “resultant values of the mandated size features can be correlated or compared in a step 20 with values deposited in a databank for the mandated size features of known toners which have been measured in respect of these size features as a preliminary stage” in order to identify a match ([0117-0118]).
That is, Bischoff discloses wherein cumulative distributions are generated to determine the distribution of the particle sizes across the sub-images ([0106-0115] discloses grouping similarly-sized sparkle points together and evaluating each group statistically before accumulating the statistics to produce the size distribution 18) and that the matching of the features present in the target coating is performed using the generated cumulative distributions of the particle sizes across the sub-images ([0117-0118]) discloses that the size distribution 18 formed by accumulating the statistics of the similarly-sized groups is compared with values deposited in a databank for the mandated size features of known toners which have been measured in advance in order to identify a match).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the claims of the ‘171 patent to extract a size distribution of particles characterized by average and standard deviation values of similarly-sized groups of particles which are each evaluated statistically and accumulated to form the size distribution, and to use the extracted size distribution as the basis for comparison with known features to identify a color match, as taught by Bischoff, to arrive at the claimed invention discussed above. Such a modification is the result of combining prior art elements according to known methods to yield predictable results. It is predictable that the proposed modification would have enhanced recognition accuracy by virtue of comparing more particular features.
As to claim 2, claim 1 of the ‘171 patent requires that the texture features include visual irregularities associated with the target image (“wherein the texture features include visual irregularities associated with the target image”).
As to claim 3, claim 2 of the ‘171 patent requires that the texture features include one or more in combination of the following characteristics: coarseness, gloss, micro-brilliance, cloudiness, mottle, speckle, sparkle, and glitter (“wherein the texture features include one or more in combination of the following characteristics: coarseness, gloss, micro-brilliance, cloudiness, mottle, speckle, sparkle, and glitter”).
As to claim 4, claim 3 of the ‘171 patent requires that the texture features do not include roughness associated with the target image (“wherein the texture features do not include roughness associated with the target image”).
As to claim 5, claim 4 of the ‘171 patent requires that the one or more data processors are configured to execute instructions to retrieve the machine learning model to determine the matching of the texture features (“wherein the one or more data processors are configured to execute instructions to retrieve the machine learning model to determine the matching of the texture features”).
As to claim 6, claim 5 of the ‘171 patent requires that the machine-learning model is a convolutional neural network configured to extract and analyze the texture features (“wherein the machine-learning model is a convolutional neural network configured to extract and analyze the texture features”).
As to claim 7, claim 6 of the ‘171 patent requires that the determined texture features of the target coating are used to determine the distribution of coarseness across the target coating (“wherein color population, the determined texture features of the target coating, and color differences across the target image are used to determine distribution of coarseness across the target coating”).
As to claim 8, claim 7 of the ‘171 patent requires that the one or more data processors are configured to receive the target image data of the target coating, wherein the target image data corresponds to a plurality of images of the target coating with varying angles of light relative to an imaging device (“wherein the one or more data processors are configured to receive the target image data of the target coating, wherein the target image data corresponds to a plurality of images of the target coating with varying angles of light relative to an imaging device”).
As to claim 9, claim 8 of the ’171 patent requires that the one or more data processors are configured to receive the target image data of the target coating, wherein the target image data correlates to a plurality of images of the target coating with varying magnification (“wherein the one or more data processors are configured to receive the target image data of the target coating, wherein the target image data correlates to a plurality of images of the target coating with varying magnification”).
As to claim 10, claim 9 of the ‘171 patent requires that the target coating is a metallic coating, a pearlescent coating, or a combination thereof (“wherein the target coating is a metallic coating, a pearlescent coating, or a combination thereof”).
As to independent claim 11, claim 10 of the ‘171 patent requires a method for matching texture of a target coating comprising (“A method for matching texture of a target coating comprising”): receiving, by one or more data processors, a target image of the target coating, wherein the target image comprises target image data (“receiving, by one or more data processors, a target image of the target coating, wherein the target image comprises target image data”); applying, by the one or more data processors, a texture feature extraction analysis process to the target image data to determine target image texture features, wherein the texture feature extraction analysis process includes determining distribution of particle sizes within sub-images of the target image, wherein a data spread statistical measure and a center statistical measure are determined to indicate the distribution of particle sizes within the sub-images (“applying, by the one or more data processors, a texture feature extraction analysis process to the target image data to determine target image texture features, wherein the texture feature extraction analysis process includes determining distribution of particle sizes within sub-images of the target image, wherein a data spread statistical measure and a center statistical measure are determined to indicate the distribution of particle sizes”); determining, by the one or more data processors, target image texture features for the sub-images, and applying, by the one or more data processors, a machine learning model to match texture features present in the target coating using the determined target image texture features (“determining, by the one or more data processors, target image texture features for the sub-images, wherein a sub-image includes different particles, and applying, by the one or more data processors, a machine learning model to match texture features present in the target coating using the determined target image texture features”).
The claims of the ‘171 patent do not require wherein cumulative distributions are generated to determine the distribution of the particle sizes across the sub-images or that the matching of the features present in the target coating is performed using the generated cumulative distributions of the particle sizes across the sub-images.
Bischoff, like the claims of the ‘171 patent, is directed to identifying a formulation for a coating in an image by extracting features therein for comparison with known coating formulations to identify a best match (Abstract and [0011, 0036-0037, 0070-0071]). Similar to the claims of the ‘171 patent, Bischoff contemplates an image segmentation procedure prior to the feature extraction process. Specifically, Bischoff discloses that the images is segmented on the basis of contiguous areas, and the segments are handed over for blob detection in which regions within the image that differ from the surrounding regions in particular qualities are identified ([0101-0104]). Within the detected blobs, individual sparkle points are recognized, and “at least one size feature can then be determined” for each sparkle point ([0105]). The “determined values of the respective size features of all the sparkle points are then…evaluated statistically” so that “sparkle points having values of similar magnitude for the size features considered can be grouped together” and the “average area…, average diameter…, standard deviation of the areas…, [and] standard deviation of the diameters” are determined for each group, thereby “produc[ing] a size distribution 18 of the sparkle points” ([0106-0115]). Finally, the “resultant values of the mandated size features can be correlated or compared in a step 20 with values deposited in a databank for the mandated size features of known toners which have been measured in respect of these size features as a preliminary stage” in order to identify a match ([0117-0118]).
That is, Bischoff discloses wherein cumulative distributions are generated to determine the distribution of the particle sizes across the sub-images ([0106-0115] discloses grouping similarly-sized sparkle points together and evaluating each group statistically before accumulating the statistics to produce the size distribution 18) and that the matching of the features present in the target coating is performed using the generated cumulative distributions of the particle sizes across the sub-images ([0117-0118]) discloses that the size distribution 18 formed by accumulating the statistics of the similarly-sized groups is compared with values deposited in a databank for the mandated size features of known toners which have been measured in advance in order to identify a match).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the claims of the ‘171 patent to extract a size distribution of particles characterized by average and standard deviation values of similarly-sized groups of particles which are each evaluated statistically and accumulated to form the size distribution, and to use the extracted size distribution as the basis for comparison with known features to identify a color match, as taught by Bischoff, to arrive at the claimed invention discussed above. Such a modification is the result of combining prior art elements according to known methods to yield predictable results. It is predictable that the proposed modification would have enhanced recognition accuracy by virtue of comparing more particular features.
As to claim 12, claim 10 of the ‘171 patent requires that the texture features include visual irregularities associated with the target image (“wherein the texture features include visual irregularities associated with the target image”).
As to claim 13, claim 11 of the ‘171 patent requires that the texture features include one or more in combination of the following characteristics: coarseness, gloss, micro-brilliance, cloudiness, mottle, speckle, sparkle, and glitter (“wherein the texture features include one or more in combination of the following characteristics: coarseness, gloss, micro-brilliance, cloudiness, mottle, speckle, sparkle, and glitter”).
As to claim 14, claim 12 of the ‘171 patent requires that the texture features do not include roughness associated with the target image (“wherein the texture features do not include roughness associated with the target image”).
As to claim 15, claim 13 of the ‘171 patent requires that the one or more data processors are configured to execute instructions to retrieve the machine learning model to determine the matching of the texture features (“wherein the one or more data processors are configured to execute instructions to retrieve the machine learning model to determine the matching of the texture features”).
As to claim 16, claim 14 of the ’171 patent requires that the machine-learning model is a convolutional neural network configured to extract and analyze the texture features (“wherein the machine-learning model is a convolutional neural network configured to extract and analyze the texture features”).
As to claim 17, claim 15 of the ‘171 patent requires that the determined texture features of the target coating are used to determine the distribution of coarseness across the target coating (“wherein color population, the determined texture features of the target coating, and color differences across the target image are used to determine distribution of coarseness across the target coating”).
As to claim 18, claim 16 of the ‘171 patent requires that the one or more data processors are configured to receive the target image data of the target coating, wherein the target image data corresponds to a plurality of images of the target coating with varying angles of light relative to an imaging device (“wherein the one or more data processors are configured to receive the target image data of the target coating, wherein the target image data corresponds to a plurality of images of the target coating with varying angles of light relative to an imaging device”).
As to claim 19, claim 17 of the ‘171 patent requires that the one or more data processors are configured to receive the target image data of the target coating, wherein the target image data correlates to a plurality of images of the target coating with varying magnification (“wherein the one or more data processors are configured to receive the target image data of the target coating, wherein the target image data correlates to a plurality of images of the target coating with varying magnification”).
As to claim 20, claim 18 of the ‘171 patent requires that the target coating is a metallic coating, a pearlescent coating, or a combination thereof (“wherein the target coating is a metallic coating, a pearlescent coating, or a combination thereof”).
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
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.
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.
This application currently names joint inventors. In considering patentability of the claims the examiner presumes that the subject matter of the various claims was commonly owned as of the effective filing date of the claimed invention(s) absent any evidence to the contrary. Applicant is advised of the obligation under 37 CFR 1.56 to point out the inventor and effective filing dates of each claim that was not commonly owned as of the effective filing date of the later invention in order for the examiner to consider the applicability of 35 U.S.C. 102(b)(2)(C) for any potential 35 U.S.C. 102(a)(2) prior art against the later invention.
Claims 1-5, 8, 10-15, 18, and 20 are rejected under 35 U.S.C. 103 as being unpatentable over U.S. Patent Application Publication No. 2007/0172113 to Sai at al. (cited in the IDS filed 10/28/25; hereinafter “Sai”) in view of U.S. Patent Application Publication No. 2022/0107222 to Bischoff (hereinafter “Bischoff”).
As to independent claim 1, Sai discloses a system for matching texture of a target coating (Abstract discloses that Sai is directed to identifying an effective pigment based on extracted image characteristic parameters and a pre-prepared database that stores information on various kinds of effective pigments; [0063-0064] discloses that the effective pigment may include coating compositions; [0096] discloses that image characteristic parameters include particle smoothness which is a measure of texture) comprising: a storage device for storing instructions; one or more data processors configured to execute instructions ([0067] discloses memory 12 which stores a program which is executed by CPU 11) to: receive a target image of the target coating, wherein the target image comprises target image data ([0069, 0111] discloses obtaining an image of an effective pigment); apply a texture feature extraction analysis process to the target image data to determine target image texture features, wherein the texture feature extraction analysis process includes determining features within sub-images of the target image ([0079-0084, 0112-0113] disclose cropping sub-images from the image and extracting image characteristic parameters of the effective pigment therefrom; [0096] discloses that the extracted image characteristic parameters include particle smoothness which is a measure of texture; see Fig. 3); determine target image texture features for the sub-images, and apply a machine learning model to match texture features present in the target coating using the determined target image texture features ([0096] discloses extracting image characteristic parameters including particle smoothness from the cropped images; [0102-0105, 0115-0117] disclose inputting the extracted image characteristic parameters to a trained neural network which outputs information on the brand, etc. of a known effective pigment that matches most closely to the input effective pigment).
Sai does not expressly disclose that the texture feature extraction analysis process includes determining distribution of particle sizes, wherein a data spread statistical measure and a center statistical measure are determined to indicate the distribution of particle sizes within the sub-images; wherein cumulative distributions are generated to determine the distribution of the particle sizes across the sub-images or that the matching of the features present in the target coating is performed using the generated cumulative distributions of the particle sizes across the sub-images.
Bischoff, like Sai, is directed to identifying a formulation for a coating in an image by extracting features therein for comparison with known coating formulations to identify a best match (Abstract and [0011, 0036-0037, 0070-0071]). Similar to Sai, Bischoff contemplates an image segmentation procedure prior to the feature extraction process. Specifically, Bischoff discloses that the images is segmented on the basis of contiguous areas, and the segments are handed over for blob detection in which regions within the image that differ from the surrounding regions in particular qualities are identified ([0101-0104]). Within the detected blobs, individual sparkle points are recognized, and “at least one size feature can then be determined” for each sparkle point ([0105]). The “determined values of the respective size features of all the sparkle points are then…evaluated statistically” so that “sparkle points having values of similar magnitude for the size features considered can be grouped together” and the “average area…, average diameter…, standard deviation of the areas…, [and] standard deviation of the diameters” are determined for each group, thereby “produc[ing] a size distribution 18 of the sparkle points” ([0106-0115]). Finally, the “resultant values of the mandated size features can be correlated or compared in a step 20 with values deposited in a databank for the mandated size features of known toners which have been measured in respect of these size features as a preliminary stage” in order to identify a match ([0117-0118]).
That is, Bischoff discloses that the texture feature extraction analysis process includes determining distribution of particle sizes ([0116] discloses producing a “size distribution 18 of the sparkle points”), wherein a data spread statistical measure and a center statistical measure are determined to indicate the distribution of particle sizes within the sub-images ([0101-0105] discloses segmenting the image into segments, then blobs within which the sparkle points are detected; [0106-0115] discloses computing the average area, average diameter (center statistical measures) and standard deviation of areas and standard deviation of diameters (data spread statistical measures) of the sparkle points to produce the size distribution 18); wherein cumulative distributions are generated to determine the distribution of the particle sizes across the sub-images ([0106-0115] discloses grouping similarly-sized sparkle points together and evaluating each group statistically before accumulating the statistics to produce the size distribution 18) and that the matching of the features present in the target coating is performed using the generated cumulative distributions of the particle sizes across the sub-images ([0117-0118]) discloses that the size distribution 18 formed by accumulating the statistics of the similarly-sized groups is compared with values deposited in a databank for the mandated size features of known toners which have been measured in advance in order to identify a match).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Sai to extract a size distribution of particles across segmented blobs of the image characterized by average and standard deviation values of similarly-sized groups of particles which are each evaluated statistically and accumulated to form the size distribution, and to use the extracted size distribution as the basis for comparison with known features to identify a color match, as taught by Bischoff, to arrive at the claimed invention discussed above. Such a modification is the result of combining prior art elements according to known methods to yield predictable results. It is predictable that the proposed modification would have enhanced recognition accuracy by virtue of comparing more particular features.
As to claim 2, Sai as modified above further teaches that the texture features include visual irregularities associated with the target image ([0094] of Sai discloses that the extracted image characteristics include particle surface irregularity).
As to claim 3, Sai as modified above further teaches that the texture features include one or more in combination of the following characteristics: coarseness, gloss, micro-brilliance, cloudiness, mottle, speckle, sparkle, and glitter ([0017] of Bischoff discloses that the extracted features are sparkle/gloss points; the reasons for combining the references are the same as those discussed above in conjunction with claim 1).
As to claim 4, Sai as modified above further teaches that the texture features do not include roughness associated with the target image (Sai and Bischoff are both silent about features including roughness).
As to claim 5, Sai as modified above further teaches that the one or more data processors are configured to execute instructions to retrieve the machine learning model to determine the matching of the texture features ([0108] of Sai discloses that the trained neural network is stored in recording device 13 from where it must be retrieved to perform the disclosed algorithm for identifying the effective pigment that matches most closely to the input effective pigment; see [0115-0117]; [0067] discloses that the program instructions are executed by CPU 11).
As to claim 8 Sai does not expressly disclose that the one or more data processors are configured to receive the target image data of the target coating, wherein the target image data corresponds to a plurality of images of the target coating with varying angles of light relative to an imaging device.
However, Bischoff discloses that the one or more data processors are configured to receive the target image data of the target coating, wherein the target image data corresponds to a plurality of images of the target coating with varying angles of light relative to an imaging device (Fig. 1 and [0073] discloses recording the images at “one, some or all of the possible angles of illumination that are shown in FIG. 1” relative to the imaging device 120).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Sai to capture multiple images at multiple angles of illumination, as taught by Bischoff, to arrive at the claimed invention discussed above. Such a modification is the result of combining prior art elements according to known methods to yield predictable results. It is predictable that the proposed modification would have made it “possible to identify effect pigments on the basis of their different orientation relative to the surface of the target coating”, as taught by Bischoff ([0076]).
As to claim 10, Sai as modified above further teaches that the target coating is a metallic coating, a pearlescent coating, or a combination thereof ([0110] of Sai discloses that the effective pigment is contained in a metallic or pearl coating).
Independent claim 11 recites a method comprising steps performed by the system recited in independent claim 1. Accordingly, claim 11 is rejected for reasons analogous to those discussed above in conjunction with claim 1.
Claims 12-15, 18, and 20 recite features nearly identical to those recited in claims 2-5, 8, and 10, respectively. Accordingly, claims 12-15, 18, and 20 are rejected for reasons analogous to those discussed above in conjunction with claims 2-5, 8, and 10, respectively.
Claims 6 and 16 are rejected under 35 U.S.C. 103 as being unpatentable over Sai in view of Bischoff and further in view of “Using Filter Banks in Convolutional Neural Networks for Texture Classification” by Andrearczyk et al. (hereinafter “Andrearczyk”).
As to claim 6, the proposed combination of Sai and Bischoff does not expressly disclose that the machine-learning model is a convolutional neural network configured to extract and analyze the texture features. However, Andrearczyk discloses that it was well known in the imaging processing arts to use a convolutional neural network CNN to extract and analyze texture features in an image (Abstract). It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the proposed combination of Sai and Bischoff to use a CNN to extract and analyze the texture features, as taught by Andrearczyk, to arrive at the claimed invention discussed above. Such a modification is the result of combining prior art elements according to known methods to yield predictable results. It is predictable that the proposed modification would have enhanced texture extraction accuracy.
Claim 16 recites features nearly identical to those recited in claim 6. Accordingly, claim 16 is rejected for reasons analogous to those discussed above in conjunction with claim 6.
Claims 7 and 17 are rejected under 35 U.S.C. 103 as being unpatentable over Sai in view of Bischoff and further in view of U.S. Patent No. 10,352,692 to Kato (hereinafter “Kato”).
As to claim 7, the proposed combination of Sai and Bischoff does not expressly disclose that the determined texture features of the target coating are used to determine the distribution of coarseness across the target coating.
Kato, like Sai, is directed to analyzing texture features of an imaged object (Abstract). In particular, Kato discloses calculating the roughness index of an imaged surface based on color differences, surface values, and a color space histogram distribution (Abstract).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the proposed combination of Sai and Bischoff to determine a roughness (coarseness) index of the imaged object using color differences, surface values, and a color space histogram distribution, as taught by Kato, to arrive at the claimed invention discussed above. Such a modification is the result of combining prior art elements according to known methods to yield predictable results. It is predictable that the proposed modification would have provided a more robust recognition system by virtue of evaluating more features.
Claim 17 recites features nearly identical to those recited in claim 7. Accordingly, claim 17 is rejected for reasons analogous to those discussed above in conjunction with claim 7.
Claims 9 and 19 are rejected under 35 U.S.C. 103 as being unpatentable over Sai in view of Rodrigues and Bischoff and further in view of U.S. Patent Application Publication No. 2018/0322327 to Smith et al. (hereinafter “Smith”).
As to claim 9, the proposed combination of Sai, Rodrigues and Bischoff does not expressly disclose that the one or more data processors are configured to receive the target image data of the target coating, wherein the target image data correlates to a plurality of images of the target coating with varying magnification.
Smith, like Sai, is directed to machine learning classification of imaged objects (Abstract). Specifically, Smith discloses capturing a plurality of images of the same region for inspection at different magnifications for use in classifying or detecting different size particles ([0048]).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the proposed combination of Sai and Bischoff to capture images of the object of inspection at multiple magnifications and to use the images for the classification/detection task, as taught by Smith, to arrive at the claimed invention discussed above. Such a modification is the result of combining prior art elements according to known methods to yield predictable results. It is predictable that the proposed modification would have improved accuracy of classification/detection ([0048] of Smith).
Claim 19 recites features nearly identical to those recited in claim 9. Accordingly, claim 19 is rejected for reasons analogous to those discussed above in conjunction with claim 9.
Pertinent Art
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Takano (U.S. Patent Application Publication No. 2005/0141002) contemplates the subdivision of an image into sub-regions within which statistics are accumulated for combination into a distribution representative of the image.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to SEAN M CONNER whose telephone number is (571)272-1486. The examiner can normally be reached 10 AM - 6 PM Monday through Friday, and some Saturday afternoons.
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, Greg Morse can be reached at (571) 272-3838. 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.
/SEAN M CONNER/Primary Examiner, Art Unit 2663
Prosecution Insights