DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
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.
Notice of Amendment
In response to the amendment(s) filed on 11/12/25, amended claim(s) 1, 7, 11, and 23-24 is/are acknowledged. The following new and/or reiterated ground(s) of rejection is/are set forth:
Claim Objections
Claim 11 is objected to because of the following informalities: “receiving,” (line 3) appears that it should be “receiving”.
Appropriate correction is required.
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.
Claim(s) 1-24 is/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.
For claim 1, the claim language “a skin-based learning model, accessible by the imaging app, comprising a machine learning model and trained with a supervised learning algorithm, the supervised learning algorithm inputting as training data each of (a) pixel data of a plurality of training images depicting skin of respective individuals and (b) one or more spot features of skin regions of the respective individuals, wherein the supervised learning algorithm configures weights of the skin-based learning model to output one or more spot classifications corresponding to the one or more spot features of the skin regions of the respective individuals” does not appear to be 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 pre-AIA the inventor(s), at the time the application was filed, had possession of the claimed invention. A claim may lack written description when the specification does not disclose the computer and the algorithm (i.e., the necessary steps and/or flowcharts) that perform the claimed function in sufficient detail such that one of ordinary skill in the art can reasonably conclude that the inventor invented the claimed subject matter. See MPEP 2161.01(I). Here, the claim recites the function of output one or more spot classifications corresponding to the one or more spot features of the skin regions of the respective individuals, but the specification never discloses the necessary steps and/or flowcharts of how this occurs. The term “machine learning model” is treated as a black box and the specification does not describe the specifics of how to achieve the above-recited function(s) with this algorithm. For example, how many and what types of layers are there? How is the data propagated? What logics are programmed to help the machine learning algorithm make a decision? What are the weightings? Are other training concepts used such as regression? What strategies are employed to minimize the loss function? How is the clustering problem solved? It is not enough that a skilled artisan could devise a way to accomplish the function because this is not relevant to the issue of whether the inventor has shown possession of the claimed invention. See MPEP 2161.01(I). Therefore, adequate disclosure is needed.
For claim 23, the claim language “wherein the skin-based learning model comprises a machine learning model and trained with a supervised learning algorithm, the supervised learning algorithm inputting as training data each of (a) pixel data of a plurality of training images depicting skin of respective individuals and (b) one or more spot features of skin regions of the respective individuals, wherein the supervised learning algorithm configures weights of the skin-based learning model to output one or more spot classifications corresponding to the one or more spot features of the skin regions of the respective individuals” does not appear to be 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 pre-AIA the inventor(s), at the time the application was filed, had possession of the claimed invention. A claim may lack written description when the specification does not disclose the computer and the algorithm (i.e., the necessary steps and/or flowcharts) that perform the claimed function in sufficient detail such that one of ordinary skill in the art can reasonably conclude that the inventor invented the claimed subject matter. See MPEP 2161.01(I). Here, the claim recites the function of output one or more spot classifications corresponding to the one or more spot features of the skin regions of the respective individuals, but the specification never discloses the necessary steps and/or flowcharts of how this occurs. The term “machine learning model” is treated as a black box and the specification does not describe the specifics of how to achieve the above-recited function(s) with this algorithm. For example, how many and what types of layers are there? How is the data propagated? What logics are programmed to help the machine learning algorithm make a decision? What are the weightings? Are other training concepts used such as regression? What strategies are employed to minimize the loss function? How is the clustering problem solved? It is not enough that a skilled artisan could devise a way to accomplish the function because this is not relevant to the issue of whether the inventor has shown possession of the claimed invention. See MPEP 2161.01(I). Therefore, adequate disclosure is needed.
For claim 24, the claim language “wherein the skin-based learning model comprises a machine learning model and has been trained with a supervised learning algorithm, the supervised learning algorithm inputting as training data each of (a) pixel data of a plurality of training images depicting skin of respective individuals and (b) one or more spot features of skin regions of the respective individuals, wherein the supervised learning algorithm configures weights of the skin-based learning model to output one or more spot classifications corresponding to the one or more spot features of the skin regions of the respective individuals” does not appear to be 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 pre-AIA the inventor(s), at the time the application was filed, had possession of the claimed invention. A claim may lack written description when the specification does not disclose the computer and the algorithm (i.e., the necessary steps and/or flowcharts) that perform the claimed function in sufficient detail such that one of ordinary skill in the art can reasonably conclude that the inventor invented the claimed subject matter. See MPEP 2161.01(I). Here, the claim recites the function of output one or more spot classifications corresponding to the one or more spot features of the skin regions of the respective individuals, but the specification never discloses the necessary steps and/or flowcharts of how this occurs. The term “machine learning model” is treated as a black box and the specification does not describe the specifics of how to achieve the above-recited function(s) with this algorithm. For example, how many and what types of layers are there? How is the data propagated? What logics are programmed to help the machine learning algorithm make a decision? What are the weightings? Are other training concepts used such as regression? What strategies are employed to minimize the loss function? How is the clustering problem solved? It is not enough that a skilled artisan could devise a way to accomplish the function because this is not relevant to the issue of whether the inventor has shown possession of the claimed invention. See MPEP 2161.01(I). Therefore, adequate disclosure is needed.
Dependent claim(s) 2-22 fail to cure the deficiencies of independent claim 1, thus claim(s) 1-24 is/are rejected under 35 U.S.C. 112(a).
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.
Claim(s) 7 is/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.
For claim 7, the claim language “wherein each image of the one or more of the plurality of training images comprises multiple angles or perspectives depicting skin regions of the respective individuals or the user” is ambiguous. It is unclear what the scope of one “image” comprising “multiple angles or perspectives” means. For example, does it mean a collage of images that show multiple angles or perspectives but the collage is the overall “image”? The claim is examined as meaning multiple images comprises multiple angles or perspectives.
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
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.
Claim(s) 1, 6, 8-13, 15-17, and 21-24 is/are rejected under 35 U.S.C. 103 as being unpatentable over U.S. Patent Application Publication No. 2020/0178881 to Purwar et al. (hereinafter “Purwar”) in view of U.S. Patent Application Publication No. 2020/0294234 to Rance et al. (hereinafter “Rance”).
For claim 1, Purwar disclose a digital imaging and artificial intelligence-based system configured to analyze pixel data of an image of user skin to generate one or more user-specific skin spot classifications (Abstract), the digital imaging and artificial intelligence-based system comprising:
one or more processors (“processor,” para [0005]);
an imaging application (app) comprising computing instructions configured to execute on the one or more processors (para [0053]-[0054] and [0056]); and
a skin-based learning model (Examiner’s Note: construed in view of page 21, lines 6-18 of Applicant’s specification as originally filed) (para [0040]), accessible by the imaging app (as can be seen in Fig. 1), comprising a machine learning model (para [0040]) configured to output one or more spot classifications corresponding to one or more spot features of skin regions of the respective individuals (para [0040]),
wherein the computing instructions of the imaging app when executed by the one or more processors, cause the one or more processors to:
receive an image of a user, the image comprising a digital image as captured by an imaging device, and the image comprising pixel data of at least a portion of a skin region of the user (850) (Fig. 8) (para [0051]),
analyze, by the skin-based learning model, the image as captured by the imaging device to determine at least one spot classification of the user’s skin, the at least one spot classification selected from the one or more spot classifications of the skin-based learning model (852-854) (Fig. 8) (para [0051]) (also see para [0040]), and
generate, based on the at least one spot classification of the user’s skin, a user-specific skin recommendation designed to address at least one spot feature identifiable within the pixel data comprising the portion of the skin region of the user (856) (Fig. 8) (para [0051]) (also see para [0049]).
Purwar does not expressly disclose a supervised learning algorithm, the supervised learning algorithm inputting as training data each of (a) pixel data of a plurality of training images depicting skin of respective individuals and (b) one or more spot features of skin regions of the respective individuals, wherein the supervised learning algorithm configures weights of the skin-based learning model.
However, Rance teaches a supervised learning algorithm (para [0034]), the supervised learning algorithm inputting as training data each of (a) pixel data of a plurality of training images depicting skin of respective individuals (para [0034] teaches that the supervised algorithm uses image data and para [0018] teaches that the image data includes pixel data) and (b) one or more spot features of skin regions of the respective individuals (para [0026]) (also see para [0017]), wherein the supervised learning algorithm configures weights of the skin-based learning model (para [0033] and [0037]).
It would have been obvious to a skilled artisan to modify Purwar to include a supervised learning algorithm, the supervised learning algorithm inputting as training data each of (a) pixel data of a plurality of training images depicting skin of respective individuals and (b) one or more spot features of skin regions of the respective individuals, wherein the supervised learning algorithm configures weights of the skin-based learning model, in view of the teachings of Rance, for the obvious advantage of controlling the biases of the model based on label from dermatologists or other experts so that the model generates outputs congruent with those biases. This increases user control over the model.
For claim 6, Purwar further discloses wherein each image of the one or more of the plurality of training images or the image of the user comprises at least one cropped image depicting the skin region having a single instance of a spot feature (as can be seen in Fig. 3) (also see para [0037]-[0039]).
For claim 8, Purwar further discloses wherein the computing instructions of the imaging app when executed by the one or more processors, further cause the one or more processors to: render, on a display screen of a computing device, at least one user-specific skin recommendation based on the user-specific spot classification (as can be seen in Fig. 7) (also see para [0049]).
For claim 9, Purwar further discloses wherein the at least one user-specific skin recommendation is displayed on the display screen of the computing device with instructions for treating the at least one spot feature identifiable in the pixel data comprising the portion of the skin region of the user (as can be seen in Fig. 7).
For claim 10, Purwar further discloses wherein the at least one user-specific skin recommendation comprises a textual recommendation, an imaged based recommendation, or virtual rendering of the at least the portion of the skin region of the user (as can be seen in Fig. 7).
For claim 11, Purwar further discloses wherein the at least one user-specific skin recommendation is rendered on the display screen during or after receiving the image of the user (Figs. 6-7) (para [0049]).
For claim 12, Purwar further disclose wherein the at least one user-specific spot recommendation comprises a product recommendation for a manufactured product (as can be seen in Fig. 7) (para [0049]).
For claim 13, Purwar further discloses wherein the at least one user-specific skin recommendation is displayed on the display screen of the computing device with instructions for treating, with the manufactured product, the at least one spot feature identifiable in the pixel data comprising the portion of a skin region of the user (as can be seen in Fig. 7) (para [0049]).
For claim 15, Purwar further discloses wherein the computing instructions further cause the one or more processors to: generate a modified image based on the image, the modified image depicting how the user’s skin region is predicted to appear after treating the at least one spot feature with the manufactured product (para [0050]); and render, on the display screen of the computing device, the modified image (para [0050]).
For claim 16, Purwar further discloses wherein the computing instructions of the imaging app when executed by the one or more processors, further cause the one or more processors to: generate a skin quality code as determined based on the user-specific spot classification designed to address the at least one spot feature identifiable within the pixel data comprising the portion of the skin region of the user (para [0040]).
For claim 17, Purwar further discloses wherein the computing instructions further cause the one or more processors to: record, in one or more memories communicatively coupled to the one or more processors (para [0005]), the image of the user as captured by the imaging device at a first time for tracking changes to user’s skin region over time (para [0039] and [0050]), receive a second image of the user, the second image captured by the imaging device at a second time (para [0039] and [0050]), and the second image comprising pixel data of at least a portion of a skin region of the user (para [0039] and [0050]), analyze, by the skin-based learning model, the second image captured by the imaging device to determine, at the second time, a second image classification of the user’s skin region as selected from the one or more image classifications of the skin-based learning model (para [0039] and [0050]), and generate, based on a comparison of the image and the second image and/or the image classification and the second image classification of the user’s skin region, a new user-specific spot classification regarding at least one spot feature identifiable or lack thereof within the pixel data of the second image comprising at least the portion the skin region of the user (para [0039] and [0050]).
For claim 21, Purwar further discloses wherein at least one of the one or more processors comprises a processor of a mobile device (102c), and wherein the imaging device comprises a digital camera of the mobile device (para [0027]) (also see para [0028]-[0029]).
For claim 22, Purwar further discloses wherein the one or more processors comprises a server processor of a server (104) (Fig. 1), wherein the server is communicatively coupled to a computing device via a computer network (via 100) (Fig. 1), and where the imaging app comprises a server app portion configured to execute on the one or more processors of the server (see 144 in Fig. 1) and a computing device app portion configured to execute on one or more processors of the computing device (para [0031]), the server app portion configured to communicate with the computing device app portion (as can be seen in Fig. 1), wherein the server app portion is configured to implement one or more of: (1) receiving the image captured by the imaging device; (2); determining the at least one spot classification of the user’s skin region; (3) generating the user-specific spot classification; and/or (4) transmitting a user-specific recommendation the computing device app portion (para [0031] and [0051]).
For claim 23, Purwar discloses a digital imaging and artificial intelligence-based method for analyzing pixel data of an image of user skin to generate one or more user-specific skin spot classifications (Abstract), the digital imaging and artificial intelligence-based method comprising:
receiving, at one or more processors (“processor,” para [0005]), an image of a user, the image comprising a digital image as captured by an imaging device, and the image comprising pixel data of at least a portion of a skin region of the user (850) (Fig. 8) (para [0051]);
analyzing, by a skin-based learning model (Examiner’s Note: construed in view of page 21, lines 6-18 of Applicant’s specification as originally filed) (para [0040]) executing on the one or more processors, the image as captured by the imaging device to determine at least one spot classification of the user’s skin, the at least one spot classification selected from the one or more spot classifications of the skin-based learning model (852-854) (Fig. 8) (para [0051]) (also see para [0040]);
wherein the skin-based learning model comprises a machine learning model (para [0040]) configured to output one or more spot classifications corresponding to one or more spot features of skin regions of the respective individuals (para [0040]), and
generating by the one or more processors and based on the at least one spot classification of the user’s skin, a user-specific skin recommendation designed to address at least one spot feature identifiable within the pixel data comprising the portion of the skin region of the user (856) (Fig. 8) (para [0051]) (also see para [0049]).
Purwar does not expressly disclose a supervised learning algorithm, the supervised learning algorithm inputting as training data each of (a) pixel data of a plurality of training images depicting skin of respective individuals and (b) one or more spot features of skin regions of the respective individuals, wherein the supervised learning algorithm configures weights of the skin-based learning model.
However, Rance teaches a supervised learning algorithm (para [0034]), the supervised learning algorithm inputting as training data each of (a) pixel data of a plurality of training images depicting skin of respective individuals (para [0034] teaches that the supervised algorithm uses image data and para [0018] teaches that the image data includes pixel data) and (b) one or more spot features of skin regions of the respective individuals (para [0026]) (also see para [0017]), wherein the supervised learning algorithm configures weights of the skin-based learning model (para [0033] and [0037]).
It would have been obvious to a skilled artisan to modify Purwar to include a supervised learning algorithm, the supervised learning algorithm inputting as training data each of (a) pixel data of a plurality of training images depicting skin of respective individuals and (b) one or more spot features of skin regions of the respective individuals, wherein the supervised learning algorithm configures weights of the skin-based learning model, in view of the teachings of Rance, for the obvious advantage of controlling the biases of the model based on label from dermatologists or other experts so that the model generates outputs congruent with those biases. This increases user control over the model.
For claim 24, Purwar discloses a tangible, non-transitory computer-readable medium (“memory,” para [0005]) storing instructions for analyzing pixel data of an image of user skin to generate one or more user-specific skin spot classifications (Abstract), that when executed by one or more processors cause the one or more processors to:
receive an image of a user, the image comprising a digital image as captured by an imaging device, and the image comprising pixel data of at least a portion of a skin region of the user (850) (Fig. 8) (para [0051]);
analyze, by a skin-based learning model (Examiner’s Note: construed in view of page 21, lines 6-18 of Applicant’s specification as originally filed) (para [0040]), the image as captured by the imaging device to determine at least one spot classification of the user’s skin, the at least one spot classification selected from the one or more spot classifications of the skin-based learning model (852-854) (Fig. 8) (para [0051]) (also see para [0040]),
wherein the skin-based learning model comprises a machine learning model (para [0040]) configured to output one or more spot classifications corresponding to one or more spot features of skin regions of the respective individuals (para [0040]); and
generate, based on the at least one spot classification of the user’s skin, a user-specific skin recommendation designed to address at least one spot feature identifiable within the pixel data comprising the portion of the skin region of the user (856) (Fig. 8) (para [0051]) (also see para [0049]).
Purwar does not expressly disclose a supervised learning algorithm, the supervised learning algorithm inputting as training data each of (a) pixel data of a plurality of training images depicting skin of respective individuals and (b) one or more spot features of skin regions of the respective individuals, wherein the supervised learning algorithm configures weights of the skin-based learning model.
However, Rance teaches a supervised learning algorithm (para [0034]), the supervised learning algorithm inputting as training data each of (a) pixel data of a plurality of training images depicting skin of respective individuals (para [0034] teaches that the supervised algorithm uses image data and para [0018] teaches that the image data includes pixel data) and (b) one or more spot features of skin regions of the respective individuals (para [0026]) (also see para [0017]), wherein the supervised learning algorithm configures weights of the skin-based learning model (para [0033] and [0037]).
It would have been obvious to a skilled artisan to modify Purwar to include a supervised learning algorithm, the supervised learning algorithm inputting as training data each of (a) pixel data of a plurality of training images depicting skin of respective individuals and (b) one or more spot features of skin regions of the respective individuals, wherein the supervised learning algorithm configures weights of the skin-based learning model, in view of the teachings of Rance, for the obvious advantage of controlling the biases of the model based on label from dermatologists or other experts so that the model generates outputs congruent with those biases. This increases user control over the model.
Claim(s) 2-3, 5, and 18-19 is/are rejected under 35 U.S.C. 103 as being unpatentable over Purwar in view of Rance, and further in view of “Artificial Intelligence in Cosmetic Dermatology: A Systematic Literature Review,” by Vatiwutipong et al. (hereinafter “Vatiwutipong”).
For claim 2, Purwar and Rance do not expressly disclose wherein the at least one spot feature identifiable within the pixel data or the one or more spot classifications is based on biological chromophores of skin comprising one or more of: eumelanin, pheomelanin, oxyhemoglobin, deoxyhemoglobin, bilirubin, or oxidized sebum.
However, Vatiwutipong teaches wherein the at least one spot feature identifiable within the pixel data or the one or more spot classifications is based on biological chromophores of skin comprising one or more of: eumelanin, pheomelanin, oxyhemoglobin, deoxyhemoglobin, bilirubin, or oxidized sebum (section entitled “IV. Analysis of Reviewed Papers,” subsection entitled “B. Skin Assessment” and section entitled “IV. Analysis of Reviewed Papers,” subsection entitled “Treatment Outcome Prediction”).
It would have been obvious to a skilled artisan to modify Purwar wherein the at least one spot feature identifiable within the pixel data or the one or more spot classifications is based on biological chromophores of skin comprising one or more of: eumelanin, pheomelanin, oxyhemoglobin, deoxyhemoglobin, bilirubin, or oxidized sebum, in view of the teachings of Vatiwutipong, for the obvious advantage of taking this additional variable(s) into account when Purwar is performing its analysis and making its recommendation so that a more complete and comprehensive analysis and recommendation make be performed.
For claim 3, Purwar and Rance do not expressly disclose wherein the one or more spot classifications comprise one or more of: (1) a hemoglobin type classification; or (2) a melanin type classification.
However, Vatiwutipong teaches wherein the one or more spot classifications comprise one or more of: (1) a hemoglobin type classification; or (2) a melanin type classification (section entitled “IV. Analysis of Reviewed Papers,” subsection entitled “B. Skin Assessment” and section entitled “IV. Analysis of Reviewed Papers,” subsection entitled “Treatment Outcome Prediction”).
It would have been obvious to a skilled artisan to modify Purwar wherein the one or more spot classifications comprise one or more of: (1) a hemoglobin type classification; or (2) a melanin type classification, in view of the teachings of Vatiwutipong, for the obvious advantage of taking this additional variable(s) into account when Purwar is performing its analysis and making its recommendation so that a more complete and comprehensive analysis and recommendation make be performed.
For claim 5, Purwar and Rance do not expressly disclose wherein the skin-based learning model is an ensemble-based AI model comprising (i) a segmentation model configured to generate a segmentation mapping of one or more spots in a skin region of an image, and (ii) a prediction or classification model configured to analyze the pixel data of the segmentation mapping of one or more spots, and wherein the computing instructions of the imaging app when executed by the one or more processors, further cause the one or more processors to: generate a user-specific segmentation mapping of one or more spots in the portion of the skin region of the user identifiable in the image of the user, output, by the prediction or classification model, a prediction or classification value indicating a spot type, and determine, based on the prediction or classification value, the at least one spot classification selected from the one or more spot classifications of the skin-based learning model.
However, Vatiwutipong teaches wherein the skin-based learning model is an ensemble-based AI model comprising (i) a segmentation model configured to generate a segmentation mapping of one or more spots in a skin region of an image (section entitled “IV. Analysis of Reviewed Papers,” subsection entitled “C. Skin Condition Diagnosis,” subsection entitled “2) Conditions Classification”), and (ii) a prediction or classification model configured to analyze the pixel data of the segmentation mapping of one or more spots (section entitled “IV. Analysis of Reviewed Papers,” subsection entitled “C. Skin Condition Diagnosis,” subsection entitled “2) Conditions Classification”), and wherein the computing instructions of the imaging app when executed by the one or more processors, further cause the one or more processors to: generate a user-specific segmentation mapping of one or more spots in the portion of the skin region of the user identifiable in the image of the user, output, by the prediction or classification model (section entitled “IV. Analysis of Reviewed Papers,” subsection entitled “C. Skin Condition Diagnosis,” subsection entitled “2) Conditions Classification”), a prediction or classification value indicating a spot type (section entitled “IV. Analysis of Reviewed Papers,” subsection entitled “C. Skin Condition Diagnosis,” subsection entitled “2) Conditions Classification”), and determine, based on the prediction or classification value, the at least one spot classification selected from the one or more spot classifications of the skin-based learning model (section entitled “IV. Analysis of Reviewed Papers,” subsection entitled “C. Skin Condition Diagnosis,” subsection entitled “2) Conditions Classification”).
It would have been obvious to a skilled artisan to modify Purwar wherein the skin-based learning model is an ensemble-based AI model comprising (i) a segmentation model configured to generate a segmentation mapping of one or more spots in a skin region of an image, and (ii) a prediction or classification model configured to analyze the pixel data of the segmentation mapping of one or more spots, and wherein the computing instructions of the imaging app when executed by the one or more processors, further cause the one or more processors to: generate a user-specific segmentation mapping of one or more spots in the portion of the skin region of the user identifiable in the image of the user, output, by the prediction or classification model, a prediction or classification value indicating a spot type, and determine, based on the prediction or classification value, the at least one spot classification selected from the one or more spot classifications of the skin-based learning model, in view of the teachings of Vatiwutipong, for the obvious advantage of improving predictive performance while reducing generalization error.
For claim 18, Purwar and Rance do not expressly disclose wherein the skin-based learning model is an artificial intelligence (AI) based model trained with at least one AI algorithm.
However, Vatiwutipong teaches wherein the skin-based learning model is an artificial intelligence (AI) based model trained with at least one AI algorithm (Abstract) (also see Section IV(C)(1)).
It would have been obvious to a skilled artisan to modify Purwar wherein the skin-based learning model is an artificial intelligence (AI) based model trained with at least one AI algorithm, in view of the teachings of Vatiwutipong, because an AI model is a suitable type of model that can be substituted with the model in Purwar that would lead to the predictable result of still classifying skin images.
For claim 19, Purwar and Rance do not expressly disclose wherein the one or more spot features of skin regions of the plurality of training images differ based one or more user demographics or ethnicities of the respective individuals, and wherein the user-specific spot classification of the user is generated, by the skin-based learning model, based on an ethnicity or demographic value of the user.
However, Vatiwutipong teaches wherein the one or more spot features of skin regions of the plurality of training images differ based one or more user demographics or ethnicities of the respective individuals (paragraph bridging pages 71417-71418 and first full paragraph of page 71418), and wherein the user-specific spot classification of the user is generated, by the skin-based learning model, based on an ethnicity or demographic value of the user (paragraph bridging pages 71417-71418 and first full paragraph of page 71418).
It would have been obvious to a skilled artisan to modify Purwar wherein the one or more spot features of skin regions of the plurality of training images differ based one or more user demographics or ethnicities of the respective individuals, and wherein the user-specific spot classification of the user is generated, by the skin-based learning model, based on an ethnicity or demographic value of the user, in view of the teachings of Vatiwutipong, for the obvious advantage of taking into account more variables to get a more accurate output from the model.
Claim(s) 4 is/are rejected under 35 U.S.C. 103 as being unpatentable over Purwar in view of Rance, and further in view of U.S. Patent Application Publication No. 2014/0226900 to Saban et al. (hereinafter “Saban”).
For claim 4, Purwar and Rance do not expressly disclose wherein an image calibration algorithm is applied to each of the plurality of training images to alter the images to enhance spot classification, and wherein the computing instructions of the imaging app when executed by the one or more processors, further cause the one or more processors to: apply the image calibration algorithm to the image of the user prior to analyzing, with the skin-based learning model, the image of the user.
However, Saban teaches wherein an image calibration algorithm is applied to images to enhance the images (para [0072]-[0073], [0079], and [0081]) to enhance spot classification (para [0063]), and wherein the computing instructions of the imaging app when executed by the one or more processors, further cause the one or more processors to: apply the image calibration algorithm to the image of the user prior to analyzing the image of the user (para [0072]-[0073], [0079], and [0081]) (also see para [0063]).
It would have been obvious to a skilled artisan to modify Purwar wherein an image calibration algorithm is applied to each of the plurality of training images to alter the images to enhance spot classification, and wherein the computing instructions of the imaging app when executed by the one or more processors, further cause the one or more processors to: apply the image calibration algorithm to the image of the user prior to analyzing, with the skin-based learning model, the image of the user, in view of the teachings of Saban, to increase accuracy of the depiction of the images.
Claim(s) 7 is/are rejected under 35 U.S.C. 103 as being unpatentable over Purwar in view of Rance, and further in view of U.S. Patent Application Publication No. 2014/0313303 to Davis et al. (hereinafter “Davis”).
For claim 7, Purwar and Rance do not expressly disclose wherein each image of the one or more of the plurality of training images or the image of the user comprises multiple angles or perspectives depicting skin regions of the respective individuals or the user.
However, Davis teaches wherein each image of the one or more of the plurality of training images comprises multiple angles or perspectives depicting skin regions of the respective individuals or the user (Fig. 10 and para [0232]-[0237]).
It would have been obvious to a skilled artisan to modify Purwar wherein each image of the one or more of the plurality of training images comprises multiple angles or perspectives depicting skin regions of the respective individuals or the user, in view of the teachings of Davis, for the obvious advantage of capturing images having “diversity in illumination angle, illumination spectrum, and viewpoint” (see para [0237] of Davis).
Claim(s) 14 is/are rejected under 35 U.S.C. 103 as being unpatentable over Purwar in view of Rance, and further in view of U.S. Patent Application Publication No. 2023/0196552 to Knight et al. (hereinafter “Knight”).
For claim 14, Purwar further discloses wherein the computing instructions further cause the one or more processors to: initiate, based on the at least one user-specific skin recommendation, the manufactured product to be dispensed to the user (para [0048] and [0051]).
Purwar and Rance do not expressly disclose that the dispensing is shipping.
However, Knight teaches initiating shipment of a product based on a skin recommendation (para [0081]).
It would have been obvious to a skilled artisan to modify Purwar such that dispensing is shipping, in view of the teachings of Knight, because shipment is another way to provide a product to a user than dispensing.
Claim(s) 20 is/are rejected under 35 U.S.C. 103 as being unpatentable over Purwar in view of Rance, and further in view of U.S. Patent Application Publication No. 2021/0182705 to Bates.
For claim 20, Purwar and Rance do not expressly disclose wherein the skin-based learning model is further trained with user demographic data and environment data of the respective users, and wherein the at least one spot classification, as generated by the skin-based learning model is further based on user demographic data and environment data as provided by the user.
However, Bates teaches wherein the skin-based learning model is further trained with user demographic data and environment data of the respective users (para [0041]) (also see para [0042]-[0043]), and wherein the at least one spot classification, as generated by the skin-based learning model is further based on user demographic data and environment data as provided by the user (para [0044]).
It would have been obvious to a skilled artisan to modify Purwar wherein the skin-based learning model is further trained with user demographic data and environment data of the respective users, and wherein the at least one spot classification, as generated by the skin-based learning model is further based on user demographic data and environment data as provided by the user, in view of the teachings of Bates, for the obvious advantage of taking into account more variables to get a more accurate output from the model.
Response to Arguments
Applicant’s arguments filed 11/12/25 have been fully considered.
With respect to the 112(b) rejections, Applicant’s amendments and arguments are persuasive with respect to claim 11. However, the rejection of claim 7 has been maintained since it is still ambiguous how a single image can have multiple angles and perspectives.
With respect to the 101 rejection(s), Applicant’s amendments and arguments are persuasive and thus the rejection(s) is/are withdrawn.
With respect to the 102/103 rejections, Applicant’s arguments have been considered but are moot because the arguments do not address the new grounds of rejection necessitated by Applicant’s amendments presented in the response filed 11/12/25.
Conclusion
THIS ACTION IS MADE FINAL. 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 DANIEL LEE CERIONI whose telephone number is (313) 446-4818. The examiner can normally be reached M - F 8:00 AM - 5:00 PM PT.
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, Jennifer Robertson can be reached at (571) 272-5001. 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.
/DANIEL L CERIONI/Primary Examiner, Art Unit 3791
Prosecution Insights