DETAILED ACTION
Status of Claims
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
This action is a FINAL office action in response to the Applicant’s response filed 15 September 2025.
Claims 1, 2, 4-12, 17, 19, and 20 have been amended.
The 101 rejections for claims 1-20 have been overcome by amendments.
Claim 3 has been cancelled.
Claim 21 has been added.
Claims 1, 2, and 4-21 are currently pending and have been examined.
Response to Arguments
Applicant's arguments filed 12 September 2025 with regards to the 112b rejections have been fully considered but they are not persuasive.
With respect to the previous 112b rejections, the Applicant argues on page 11 of their response, “Claims 5-7 are rejected under 35 U.S.C. 112(b) as allegedly indefinite. Applicant respectfully requests withdrawal of these rejections in view of the foregoing amendments to claims 5-7.” The Examiner respectfully disagrees with the Applicant’s interpretation of their amendments, and the grounds of the previous and current rejection. With respect to claim 5, the Applicant has amended the claim to state, “wherein the at least one similarity comprises: a textual similarity between text included on the face of the first packaging and text included on the first face of the second packaging, and a graphical similarity between the reference image and the image of the first packaging.” With respect to claim 1, the Applicant has also amended the claim to state, “capturing, at a mobile device, multiple images of first packaging using a camera of the mobile device; processing, at the mobile device, the multiple images using one or more machine learning models, wherein the one or more machine learning models have been trained to identify a face of the first packaging in the images, and identify one or more regions in the multiple images that exhibit corruption… wherein the feedback for image capture comprises a live overlay on the one or more regions in the multiple images that exhibit the corruption, the live overlay providing real-time feedback for adjustment of image capture to reduce the corruption; and in response to output of the one or more machine learning models indicating that the one or more capture conditions are satisfied for an image of the first packaging from among the multiple images of the first packaging, and in response to the output of the one or more machine learning models indicating that the face of the first packaging is present in the image, sending the image for authentication of the first packaging.” In this case, claim 5 refers to “the image of the first packaging,” however the Applicant has removed reference to “an image” of the first package in claim 1, and replaced it with “multiple images of the first packaging,” therefore rendering it unclear as to what image claim 5 is referring to with its recitation. It is noted that claim 1 does refer to “an image” in the final element of the claim, however this it is unclear as to whether claim 5 is referencing this recitation, or one of the other images referenced in the claim. The Applicant is encouraged to clarify specifically what image of the plurality of images the claim is referencing. It is noted that claims 6 and 7 have similar deficiencies, and thus, are still rejected. Therefore, the Examiner maintains that this rejection is proper.
Applicant’s arguments with respect to claims 1, 19, and 20 with regards to identifying corruption in images 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.
Applicant's arguments filed 12 September 2025 with respect to the dependent claims have been fully considered but they are not persuasive.
With respect to the claims, the Applicant argues on page 13 of their response:
“Applicant also requests particular reconsideration with respect to several dependent claims:
Claim 2 is amended to recite that “the one or more machine learning models have been trained to determine whether a face type of the face of the first packaging is a front face or arear face.” The cited references have not been shown to teach such a machine learning model.
Claims 4, 7, and 10-12 have been amended, and withdrawal of the rejections thereof is respectfully requested.
The cited references fail to disclose or render obvious the subject matter of claim 13. The Office argues that Heikel “describe[s] training machine learning models in order recognize packages in images, wherein original images of an original product are collected and used to train a model to recognize the packages, including using different orientations of images.” Office Action, 21. But Heikel fails to disclose, for example, “generating a plurality of images by modifying at least one of orientation, background, or contrast of the image of the reference packaging.” Heikel at most discloses, for example, “turning the camera or the administrator device 30 in different angles during taking the original product video.” Heikel, [0160].”
The Examiner respectfully disagrees with the Applicant’s interpretation of the cited prior art of record, and the broadest reasonable interpretation of the claimed invention. First, with respect to claims 2, 4, 7, and 10-12, Applicant's arguments fail to comply with 37 CFR 1.111(b) because they amount to a general allegation that the claims define a patentable invention without specifically pointing out how the language of the claims patentably distinguishes them from the references. In this case, the Applicant has merely generally referenced the recited claims, and stated that the prior art does not teach the elements, and that reconsideration is requested. With regards to this argument, the mere assertion that the prior art does not disclose the elements, is found not persuasive, as the current amendments do not change the scope of these claims, and the previously cited prior art discloses the elements, as noted in the Non-Final Rejection. With regards to claim 13, the Applicant’s argument that Heikel fails to disclose, “generating a plurality of images by modifying at least one of orientation, background, or contrast of the image of the reference packaging,” the Examiner is not persuaded. With regards to Heikel states in paragraph 155, “FIG. 7A shows one original pharmaceutical product 700, which is a pharmaceutical product package. The original pharmaceutical product 700 may have two or more different features which may be identified separately or together. In FIG. 16A, the original product has at least the following features when a first side or surface 702 of the original pharmaceutical product is viewed: shape, or dimensions, or contour 704 of the original pharmaceutical product, visual symbols 706 and written text feature 708. Anyone or all of these features may be separately or in combination identified.” (Emphasis added). Heikel continues in paragraph 157, “In some embodiments, the administrator interface 32 may instruct in taking the original product video. Accordingly, the administrator device 30 or the administrator interface 32 may instruct, by utilizing instructions stored in the administrator device memory 35 and executed by the administrator device processor 36, in taking the original product video. The administrator interface 32 in the administrator device 30 of the system 1 may be operable to instruct the administrator in taking the original product video.” Heikel continues in paragraph 160, “According to the above mentioned, the original product video may be instructed to be taken in one angle or turning the camera or the administrator device 30 in different angles during taking the original product video.” As shown and emphasized here, Heikel has disclosed trainings models to recognize packages by obtaining multiple images of packages, wherein the images are generated by modifying the orientation of the reference image. In this case, by having the user change the angle of their device/the package being record, multiple orientations are being obtained as it is changed, thus Heikel discloses the claimed, “generating a plurality of images by modifying at least one of orientation, background, or contrast of the image of the reference packaging.” It is noted that were the Applicant to be more specific with regards to the modifications being conducted, and how this data was used to train a model, this rejection would be reconsidered. Therefore, the Examiner maintains that this rejection is proper.
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 5-7 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.
With respect to claim 5, the Applicant claims, “wherein the at least one similarity comprises: a textual similarity between text included on the face of the first packaging and text included on the first face of the second packaging, and a graphical similarity between the reference image and the image of the first packaging.” The Applicant has rendered this claim indefinite and unclear for failing to particularly define their invention. In this case, the Applicant has referred to “the image;” however this recitation lacks antecedent basis. In particular, it is unclear as to what this recitation of “an image” refers to, as there are multiple images recited in depended upon claim 1. For the purpose of examination, the Examiner will interpret the claim to read, “wherein the at least one similarity comprises: a textual similarity between text included on the face of the first packaging and text included on the first face of the second packaging, and a graphical similarity between the reference image and the image of the first packaging that was indicated as satisfying the conditions.”
With respect to claim 6, the Applicant claims, “wherein determining whether the first packaging is authentic comprises: in response to selecting the image of the second packaging as the reference image, determining whether the first packaging is authentic based on a comparison between the first packaging in the image of the first packaging and the second packaging in the reference image.” The Applicant has rendered this claim indefinite and unclear for failing to particularly define their invention. In this case, the Applicant has referred to “the image” as both the image of the second packaging (also calling it the reference image) and as image of the first packaging; thus rendering it unclear as the same term is used for different parameters. For the purpose of examination, the Examiner will interpret the claim to read, “wherein determining whether the first packaging is authentic comprises: in response to selecting the image of the second packaging as the reference image, determining whether the first packaging is authentic based on a comparison between the image of the first packaging that was indicated as satisfying the conditions and the second packaging in the reference image.”
With respect to claim 7, the Applicant claims, “determining whether the image of the first packaging includes a data-encoding symbol; in response to determining that the image of the first packaging includes the data-encoding symbol, decoding data encoded by the data-encoding symbol; selecting, from among a plurality of images in a candidate image database, a reference image based on the data indicating a product depicted in the reference image, and determining whether the first package is authentic based on a graphical comparison between the image of the first packaging and the reference image.” The Applicant has rendered this claim indefinite and unclear for failing to particularly define their invention. In this case, the Applicant has referred to “the image of the first packaging,” however multiple images of the first packaging have been introduced in depended upon claim 1, rendering it unclear as to exactly what image this claim is referencing. For the purpose of examination, the Examiner will interpret the claim to read, “determining whether the image of the first packaging that was indicated as satisfying the conditions includes a data-encoding symbol; in response to determining that the image of the first packaging that was indicated as satisfying the conditions includes the data-encoding symbol, decoding data encoded by the data-encoding symbol; selecting, from among a plurality of images in a candidate image database, a reference image based on the data indicating a product depicted in the reference image, and determining whether the first package is authentic based on a graphical comparison between the image of the first packaging that was indicated as satisfying the conditions and the reference image.”
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, 2, 7-17, and 19-21 are rejected under 35 U.S.C. 103 as being unpatentable over Heikel et al. (US 2021/0374476 A1) (hereinafter Heikel), in view of Ryle et al. (US 2024/0378626 A1) (hereinafter Ryle), in view of Pamuru et al. (US 2023/0315373 A1) (hereinafter Pamuru).
With respect to claims 1, 19, and 20, Heikel teaches:
Capturing, at a mobile device, multiple images of first packaging using a camera of the mobile device (See at least paragraphs 135, 138-139, 157-160, 183, and 194 which describe a user using a mobile device to image a package of a product).
Processing the multiple images using one or more machine learning models; Wherein the one or more machine learning models have been trained to identify a face of the first packaging in the images (See at least paragraphs 129, 154, 194, 195, and 197-199 which describe processing the image using machine learning models in order to identify objects in the image, and determine the authenticity of the package).
Providing, at the mobile device, feedback for image capture based on a first output of the one or more machine learning models relating to one or more capture conditions; wherein the feedback for image capture comprises real-time feedback for adjustment of image capture (See at least paragraphs 186-191 which describe a user using a camera to image an item and determine the authenticity, wherein the models are used to determine if capture conditions have been met, before processing the image, including orientation and angle, and wherein instructions are provided to the user to adjust the conditions).
In response to output of the one or more machine learning models indicating that the one or more capture conditions are satisfied for an image of the first packaging from among the multiple images of the first packages, and in response to the output of the one or more machine learning models indicating that the face of the first packaging is present in the image, sending the image for authentication of the first packaging (See at least paragraphs 129, 154, 194, 195, and 197-199 which describe in response to capture conditions being satisfied, sending the image to a server and processing the image using machine learning models in order to identify objects in the image, and determine the authenticity of the package).
Heikel discloses all of the limitations of claims 1, 19, and 20 as stated above. Heikel does not explicitly disclose the following, however Ryle teaches:
Processing, at the mobile device, the image using one or more machine learning models (See at least paragraphs 44-50, 54, 56, and 69 which describe a user using their mobile device to image a package in order to determine its authenticity, wherein the mobile device uses machine learning models to analyze the image and determine if included features in the image indicate authenticity or not).
It would have been obvious to one of ordinary skill in the art at the time of filing the claimed invention to combine the system and method of using a camera of a mobile device to image a package in order to determine its authenticity, wherein the mobile device presents instructions to the user in order to image the package under the correct the conditions, wherein upon imaging the package correctly, providing the image to a server to confirm the authenticity using machine learning models of Heikel, with the system and method of a user using their mobile device to image a package in order to determine its authenticity, wherein the mobile device uses machine learning models to analyze the image and determine if included features in the image indicate authenticity or not of Ryle. By processing images of a package on a user device instead of a server, a user will predictably be able to quickly and efficiently process images of items, instead of relying on a network connection to process images.
The combination of Heikel and Ryle discloses all of the limitations of claims 1, 19, and 20 as stated above. Heikel and Ryle do not explicitly disclose the following, however Pamuru teaches:
Processing, at the mobile device, the multiple images using models, wherein the models identify one or more regions in the multiple images that exhibit corruption; providing, at the mobile device, feedback for image capture based on a first output of the models relating to one or more capture conditions; and wherein the feedback for image capture comprises a live overlay on the one or more regions in the multiple images that exhibit the corruption, the live overlay providing feedback for adjustment of image capture to reduce the corruption (See at least paragraphs 28, 29, 31, 40, 55, and 61-67 which describe processing images, using a mobile device, and machine learning models, wherein the models identify regions in the images that show features, such as glare and shadows, wherein the features are marked on the image in order to provide feedback to adjust the image and fix the features).
It would have been obvious to one of ordinary skill in the art at the time of filing the claimed invention to combine the system and method of using a camera of a mobile device to image a package in order to determine its authenticity, wherein the mobile device presents instructions to the user in order to image the package under the correct the conditions, wherein upon imaging the package correctly, providing the image to a server to confirm the authenticity using machine learning models of Heikel, with the system and method of a user using their mobile device to image a package in order to determine its authenticity, wherein the mobile device uses machine learning models to analyze the image and determine if included features in the image indicate authenticity or not of Ryle, with the system and method of processing images, using a mobile device, and machine learning models, wherein the models identify regions in the images that show features, such as glare and shadows, wherein the features are marked on the image in order to provide feedback to adjust the image and fix the features of Pamuru. By identifying portions of images with negative features, such as glare and shadows, a system will predictably be able to alert a user of aspects which hinder pictures taken from identifying the objects, and thus, predictably increasing the accuracy of the product system to identify the product.
With respect to claim 2, the combination of Heikel, Ryle, and Pamuru discloses all of the limitations of claim 1 as stated above. In addition, Heikel teaches:
Wherein the one or more machine learning models have been trained to determine a face type of the face of the first packaging of the front face or rear face (See at least paragraphs 155, 173, 175-178, 180, 185, 194, and 195 which describe using trained machine learning models to analyze images and determine authenticity, wherein the models are trained to recognize the sides of a package).
With respect to claim 7, Heikel/Ryle/Pamuru discloses all of the limitations of claim 1 as stated above. In addition, Ryle teaches:
determining whether the first packaging is authentic, wherein determining whether the first packaging is authentic comprises: determining whether the image of the first packaging includes a data-encoding symbol; in response to determining that the image of the first packaging includes the data-encoding symbol, decoding data encoded by the data-encoding symbol, selecting, from among a plurality of images in a candidate image database a reference image based on the data indicating a product depicted in the reference image, and determining whether the first packaging is authentic based on a graphical comparison between the image of the first packaging and the reference image (See at least paragraphs 44-50, 54, 56, and 69 which describe a user using their mobile device to image a package in order to determine its authenticity, wherein it is determined if the image includes a barcode/QR code, and wherein if it does, use the label to identify a reference image used for determining authenticity).
It would have been obvious to one of ordinary skill in the art at the time of filing the claimed invention to combine the system and method of using a camera of a mobile device to image a package in order to determine its authenticity, wherein the mobile device presents instructions to the user in order to image the package under the correct the conditions, wherein upon imaging the package correctly, providing the image to a server to confirm the authenticity using machine learning models of Heikel, with the system and method of a user using their mobile device to image a package in order to determine its authenticity, wherein it is determined if the image includes a barcode/QR code, and wherein if it does, use the label to identify a reference image used for determining authenticity of Ryle, with the system and method of processing images, using a mobile device, and machine learning models, wherein the models identify regions in the images that show features, such as glare and shadows, wherein the features are marked on the image in order to provide feedback to adjust the image and fix the features of Pamuru. By using an included barcode of an image to identify a reference image that can be used for determining authenticity, a system will predictably be able to quickly and efficiently identify what the object being processed is supposed to be, thus making it easier to determine authenticity.
With respect to claim 8, Heikel/Ryle/Pamuru discloses all of the limitations of claim 1 as stated above. In addition, Heikel teaches:
Determining whether the first packaging is authentic, wherein determining whether the first packaging is authentic comprises: receiving the image from the mobile device, and processing the image using a machine learning model distinct from a first machine learning model, of the one or more machine learning models, that has been trained to identify the face of the first packaging in the image (See at least paragraphs 129, 154, 194, 195, and 197-199 which describe in response to capture conditions being satisfied, sending the image to a server and processing the image using machine learning models in order to identify objects in the image, and determine the authenticity of the package, wherein multiple machine learning models are used).
With respect to claim 9, Heikel/Ryle/Pamuru discloses all of the limitations of claim 1 as stated above. In addition, Heikel teaches:
Determining whether the first packaging is authentic, wherein determining whether the first packaging is authentic comprises: determining a textual similarity between text in the image of the first packaging and text in a reference image; determining a graphical similarity between the image and the reference image; determining, based on at least one of the textual similarity or the graphical similarity, that the first packaging is not authentic; and determining, based on the image, a packaging of which the first packaging is a counterfeit (See at least paragraphs 129, 154, 194, 195, and 197-199 which describe in response to capture conditions being satisfied, sending the image to a server and processing the image using machine learning models in order to identify objects in the image, wherein when text or graphics are analyzed with the models and are compared to a profile with reference images, and wherein the target is determined to be not authentic when the image and reference image are not similar).
With respect to claim 10, Heikel/Ryle/Pamuru discloses all of the limitations of claim 1 as stated above. In addition, Pamuru teaches:
Wherein the one or more machine learning models have been trained to output a type of the corruption in the one or more regions (See at least paragraphs 28, 29, 31, 40, 55, and 61-67 which describe processing images, using a mobile device, and machine learning models, wherein the models identify regions in the images that show features, such as glare and shadows, wherein the features are marked on the image in order to provide feedback to adjust the image and fix the features).
It would have been obvious to one of ordinary skill in the art at the time of filing the claimed invention to combine the system and method of using a camera of a mobile device to image a package in order to determine its authenticity, wherein the mobile device presents instructions to the user in order to image the package under the correct the conditions, wherein upon imaging the package correctly, providing the image to a server to confirm the authenticity using machine learning models of Heikel, with the system and method of a user using their mobile device to image a package in order to determine its authenticity, wherein the mobile device uses machine learning models to analyze the image and determine if included features in the image indicate authenticity or not of Ryle, with the system and method of processing images, using a mobile device, and machine learning models, wherein the models identify regions in the images that show features, such as glare and shadows, wherein the features are marked on the image in order to provide feedback to adjust the image and fix the features of Pamuru. By identifying portions of images with negative features, such as glare and shadows, a system will predictably be able to alert a user of aspects which hinder pictures taken from identifying the objects, and thus, predictably increasing the accuracy of the product system to identify the product.
With respect to claim 11, Heikel/Ryle/Pamuru discloses all of the limitations of claim 1 as stated above. In addition, Heikel teaches:
Wherein the feedback for image capture comprises a graphical bound for placement of the first packaging during image capture, the graphical bound being moved to different locations on a display of the mobile device over capture of the multiple images (See at least paragraphs 186-191 which describe a user using a camera to image an item and determine the authenticity, wherein the models are used to determine if capture conditions have been met, before processing the image, including orientation and angle, and wherein instructions are provided to the user to adjust the conditions, including reframing objects or changing the angle of the camera).
With respect to claim 12, Heikel/Ryle/Pamuru discloses all of the limitations of claim 1 as stated above. In addition, Pamuru teaches:
Wherein the type of the corruption comprises glare or shadow (See at least paragraphs 28, 29, 31, 40, 55, and 61-67 which describe processing images, using a mobile device, and machine learning models, wherein the models identify regions in the images that show features, such as glare and shadows, wherein the features are marked on the image in order to provide feedback to adjust the image and fix the features).
It would have been obvious to one of ordinary skill in the art at the time of filing the claimed invention to combine the system and method of using a camera of a mobile device to image a package in order to determine its authenticity, wherein the mobile device presents instructions to the user in order to image the package under the correct the conditions, wherein upon imaging the package correctly, providing the image to a server to confirm the authenticity using machine learning models of Heikel, with the system and method of a user using their mobile device to image a package in order to determine its authenticity, wherein the mobile device uses machine learning models to analyze the image and determine if included features in the image indicate authenticity or not of Ryle, with the system and method of processing images, using a mobile device, and machine learning models, wherein the models identify regions in the images that show features, such as glare and shadows, wherein the features are marked on the image in order to provide feedback to adjust the image and fix the features of Pamuru. By identifying portions of images with negative features, such as glare and shadows, a system will predictably be able to alert a user of aspects which hinder pictures taken from identifying the objects, and thus, predictably increasing the accuracy of the product system to identify the product.
With respect to claim 13, Heikel/Ryle/Pamuru discloses all of the limitations of claim 1 as stated above. In addition, Heikel teaches:
Training the one or more machine learning models, wherein training the one or more machine learning models comprises: obtaining an image of reference packaging; generating a plurality of images by modifying at least one of orientation, background, or contrast of the image of the reference packaging; and training the one or more machine learning models using the plurality of images as training data (See at least paragraphs 155, 157-160, 164, 173, and 175-177 which describe training machine learning models in order recognize packages in images, wherein original images of an original product are collected and used to train a model to recognize the packages, including using different orientations of images).
With respect to claim 14, Heikel/Ryle/Pamuru discloses all of the limitations of claim 1 as stated above. In addition, Heikel teaches:
Determining whether the first packaging is authentic, wherein determining whether the first packaging is authentic comprises: comparing at least one feature of the first packaging to a digital blueprint of reference packaging, the digital blueprint comprising: a label indicating a face type of a face of the reference packaging, a graphical representation of the face of the reference packaging, and text included on the face of the reference packaging (See at least paragraphs 155, 157-160, 164, 173, and 175-177 which describe training machine learning models in order recognize packages in images, wherein original images of an original product are collected and used to train a model to recognize the packages, including using different orientations of images, wherein the reference images and labels for features in the images are stored in an item profile, including the sides, text, and graphics, which is referenced to check other items for authenticity).
With respect to claim 15, Heikel/Ryle/Pamuru discloses all of the limitations of claims 1 and 14 as stated above. In addition, Heikel teaches:
Generating the digital blueprint, wherein generating the digital blueprint comprises: processing an image of the reference packaging using a machine learning model that has been trained to determine the face type of the face of the reference packaging; and generating the digital blueprint based on an output of the machine learning model that has been trained to determine the face type of the face of the reference packaging (See at least paragraphs 155, 157-160, 164, 173, and 175-177 which describe training machine learning models in order recognize packages in images, wherein original images of an original product are collected and used to train a model to recognize the packages, including using different orientations of images, wherein the reference images and labels for features in the images are stored in an item profile, including the sides, text, and graphics, which is referenced to check other items for authenticity).
With respect to claim 16, Heikel/Ryle/Pamuru discloses all of the limitations of claim 1 as stated above. In addition, Heikel teaches:
Training the one or more machine learning models using as training data, images of faces of a plurality of packaging, and as labels for the training data, data indicative of types of faces of the plurality of packaging portrayed in the images (See at least paragraphs 155, 157-160, 164, 173, and 175-177 which describe training machine learning models in order recognize packages in images, wherein original images of an original product are collected and used to train a model to recognize the packages, including using different orientations of images, wherein the reference images and labels for features in the images are stored in an item profile, including the sides, text, and graphics, which is referenced to check other items for authenticity).
With respect to claim 17, Heikel/Ryle/Pamuru discloses all of the limitations of claim 1 as stated above. In addition, Heikel teaches:
Wherein the one or more machine learning models comprise a first machine learning model that has been trained to identify the face of the first packaging in the image, and a second machine learning model that has been trained to determine whether the first packaging in the image satisfies the one or more capture conditions (See at least paragraphs 155, 173, 175-178, 180, 185, 194, and 195 which describe using trained machine learning models to analyze images and determine authenticity, wherein the models are trained to recognize the sides of a package, which includes the front or rear of the package. Additionally, see at least paragraphs 186-191 which describe a user using a camera to image an item and determine the authenticity, wherein the models are used to determine if capture conditions have been met, before processing the image, including orientation and angle, and wherein instructions are provided to the user to adjust the conditions).
With respect to claim 21, Heikel/Ryle/Pamuru discloses all of the limitations of claim 1 as stated above. In addition, Pamuru teaches:
Wherein the one or more machine learning models are configured to output a corruption segmentation map indicative of the corruption (See at least paragraphs 28, 29, 31, 40, 55, and 61-67 which describe processing images, using a mobile device, and machine learning models, wherein the models identify regions in the images that show features, such as glare and shadows, wherein the features are marked on the image in order to provide feedback to adjust the image and fix the features).
It would have been obvious to one of ordinary skill in the art at the time of filing the claimed invention to combine the system and method of using a camera of a mobile device to image a package in order to determine its authenticity, wherein the mobile device presents instructions to the user in order to image the package under the correct the conditions, wherein upon imaging the package correctly, providing the image to a server to confirm the authenticity using machine learning models of Heikel, with the system and method of a user using their mobile device to image a package in order to determine its authenticity, wherein the mobile device uses machine learning models to analyze the image and determine if included features in the image indicate authenticity or not of Ryle, with the system and method of processing images, using a mobile device, and machine learning models, wherein the models identify regions in the images that show features, such as glare and shadows, wherein the features are marked on the image in order to provide feedback to adjust the image and fix the features of Pamuru. By identifying portions of images with negative features, such as glare and shadows, a system will predictably be able to alert a user of aspects which hinder pictures taken from identifying the objects, and thus, predictably increasing the accuracy of the product system to identify the product.
Claims 4-6 are rejected under 35 U.S.C. 103 as being unpatentable over Heikel, Ryle, and Pamuru as applied to claims 1 and 2 as stated above, and further in view of Yan et al. (US 2024/0412233 A1) (hereinafter Yan).
With respect to claim 4, Heikel/Ryle/Pamuru discloses all of the limitations of claims 1 and 2 as stated above. Heikel, Ryle, and Pamuru do not explicitly disclose the following, however Yan teaches:
Determining whether the first packaging is authentic, wherein determining whether the first packaging is authentic comprises: selecting, from two or more faces of second packaging, a first face based on the first face of the second packaging being a front face and the face of the first packaging being a front face, or based on the first face of the second packaging being a rear face and the face of the first packaging being a rear face; determining at least one similarity between the first face and the face of the first packaging; and selecting, from among a plurality of images of packaging, an image of the second packaging as a reference image based on the at least one similarity between the first face and the face of the first packaging (See at least paragraphs 26, 28, 29, 36, 40, and 48-50 which describe determining the authenticity of a target item by selecting a face of an item in reference images, determining the similarity between the target and the reference images, and selecting a reference, and comparing the features of the image and reference in order to confirm authenticity).
It would have been obvious to one of ordinary skill in the art at the time of filing the claimed invention to combine the system and method of using a camera of a mobile device to image a package in order to determine its authenticity, wherein the mobile device presents instructions to the user in order to image the package under the correct the conditions, wherein upon imaging the package correctly, providing the image to a server to confirm the authenticity using machine learning models of Heikel, with the system and method of a user using their mobile device to image a package in order to determine its authenticity, wherein the mobile device uses machine learning models to analyze the image and determine if included features in the image indicate authenticity or not of Ryle, with the system and method of processing images, using a mobile device, and machine learning models, wherein the models identify regions in the images that show features, such as glare and shadows, wherein the features are marked on the image in order to provide feedback to adjust the image and fix the features of Pamuru, with the system and method of determining the authenticity of a target item by selecting a face of an item in reference images, determining the similarity between the target and the reference images, and selecting a reference, and comparing the features of the image and reference in order to confirm authenticity of Yan. By extracting features, such as the sides, from multiple images of another package and finding the similarity to the target image features, and using a correct reference image as the image used to confirm authenticity, a system will predictably be able to quickly and efficiently be able to identify the most appropriate image to use when analyzing products for authenticity, thus making more accurate determinations.
With respect to claim 5, Heikel/Ryle/Pamuru/Yan discloses all of the limitations of claims 1, 2, and 4 as stated above. In addition, Heikel teaches:
Wherein the at least one similarity comprises: a textual similarity between text included on the face of the first packaging and text included on the first face of the second packaging, and a graphical similarity between the reference image and the image of the first packaging (See at least paragraphs 129, 154, 194, 195, and 197-199 which describe in response to capture conditions being satisfied, sending the image to a server and processing the image using machine learning models in order to identify objects in the image, wherein when text or graphics are analyzed with the models and are compared to a profile with reference images).
With respect to claim 6, Heikel/Ryle/Pamuru/Yan discloses all of the limitations of claims 1, 2, and 4 as stated above. In addition, Yan teaches:
Wherein determining whether the first packaging is authentic comprises: in response to selecting the image of the second packaging as the reference image, determining whether the first packaging is authentic based on a comparison between the first packaging in the image of the first packaging and the second packaging in the reference image (See at least paragraphs 26, 28, 29, 36, 40, and 48-50 which describe determining the authenticity of a target item by selecting a face of an item in reference images, determining the similarity between the target and the reference images, and selecting a reference, and comparing the features of the image and reference in order to confirm authenticity).
It would have been obvious to one of ordinary skill in the art at the time of filing the claimed invention to combine the system and method of using a camera of a mobile device to image a package in order to determine its authenticity, wherein the mobile device presents instructions to the user in order to image the package under the correct the conditions, wherein upon imaging the package correctly, providing the image to a server to confirm the authenticity using machine learning models of Heikel, with the system and method of a user using their mobile device to image a package in order to determine its authenticity, wherein the mobile device uses machine learning models to analyze the image and determine if included features in the image indicate authenticity or not of Ryle, with the system and method of processing images, using a mobile device, and machine learning models, wherein the models identify regions in the images that show features, such as glare and shadows, wherein the features are marked on the image in order to provide feedback to adjust the image and fix the features of Pamuru, with the system and method of determining the authenticity of a target item by selecting a face of an item in reference images, determining the similarity between the target and the reference images, and selecting a reference, and comparing the features of the image and reference in order to confirm authenticity of Yan. By extracting features, such as the sides, from multiple images of another package and finding the similarity to the target image features, and using a correct reference image as the image used to confirm authenticity, a system will predictably be able to quickly and efficiently be able to identify the most appropriate image to use when analyzing products for authenticity, thus making more accurate determinations.
Claim 18 are rejected under 35 U.S.C. 103 as being unpatentable over Heikel, Ryle, and Pamuru as applied to claim 1 as stated above, and further in view of Olaleye et al. (US 2025/0068983 A1) (hereinafter Olaleye)
With respect to claim 18, Heikel/Ryle/Pamuru discloses all of the limitations of claim 1 as stated above. In addition, Heikel teaches:
Training the one or more machine learning models, wherein training the one or more machine learning models comprises: providing, in a user interface, a display of an image of reference packaging captured by a second mobile device (See at least paragraphs 155, 157-160, 164, 173, and 175-177 which describe training machine learning models in order recognize packages in images, wherein original images of an original product are collected and used to train a model to recognize the packages, including using different orientations of images, wherein the reference images and labels for features in the images are stored in an item profile, including the sides, text, and graphics, which is referenced to check other items for authenticity).
Heikel discloses all of the limitations of claim 18 as stated above. Heikel, Ryle, and Pamuru do not explicitly disclose the following, however Olaleye teaches:
Processing the image of the reference packaging using a machine learning model that has been trained to identify a face of the reference packaging in the image of the reference packaging, to obtain, as an output, an auto-annotation indicative of at least one of text included in the face of the reference packaging, or a face type of the face of the reference packaging; Providing, in the user interface, one or more tools usable to manually alter the auto-annotation to obtain a modified annotation; and Training the one or more machine learning models using, as training data, the image of the reference packaging and the modified annotation (See at least paragraphs 38-45 which describe training a machine learning model to classify data using unlabeled training data, wherein the model initially generates labels for objects in the data, wherein the user is able to change the label annotations when determined to be incorrect, and wherein the corrected labels are used to further train the models).
It would have been obvious to one of ordinary skill in the art at the time of filing the claimed invention to combine the system and method of using a camera of a mobile device to image a package in order to determine its authenticity, wherein the mobile device presents instructions to the user in order to image the package under the correct the conditions, wherein upon imaging the package correctly, providing the image to a server to confirm the authenticity using machine learning models of Heikel, with the system and method of a user using their mobile device to image a package in order to determine its authenticity, wherein the mobile device uses machine learning models to analyze the image and determine if included features in the image indicate authenticity or not of Ryle, with the system and method of processing images, using a mobile device, and machine learning models, wherein the models identify regions in the images that show features, such as glare and shadows, wherein the features are marked on the image in order to provide feedback to adjust the image and fix the features of Pamuru, with the system and method of training a machine learning model to classify data using unlabeled training data, wherein the model initially generates labels for objects in the data, wherein the user is able to change the label annotations when determined to be incorrect, and wherein the corrected labels are used to further train the models of Olaleye. By allowing a user to manually adjust labels of features in an imaged object, generated by using a model on initial training data, and wherein the new labels are used to further train the models, a system would predictably increase the accuracy of models, by ensuring the most accurate data is used to train machine learning models.
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 P HARRINGTON whose telephone number is (571)270-1365. The examiner can normally be reached Monday-Friday 9-5.
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, Jeffrey can be reached on (571) 272-4602. 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.
Michael Harrington
Primary Patent Examiner
16 December 2025
Art Unit 3628
/MICHAEL P HARRINGTON/Primary Examiner, Art Unit 3628
Prosecution Insights