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 .
Information Disclosure Statement
The information disclosure statement (IDS) submitted on 10/07/24 was filed. The submission is in compliance with the provisions of 37 CFR 1.97. Accordingly, the information disclosure statement is being considered by the examiner.
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.
Claim(s) 50, 51, 54-58, 60, 61, 63-66, 68 is/are rejected under 35 U.S.C. 103 as being unpatentable over Moon et al US 20090285456 in view of Sung et al US 20050117783.
Regarding claim 50, Moon et al teaches a system for computer implemented assisting the identification of preferences of a user with respect to different candidates presented to the user (fig. 1), comprising:
a camera arranged and configured to capture images of the user's face (means for capturing images 100 is placed near the media display 152, so that it can capture the faces of media audience 790 watching the display (paragraph 0064). means for capturing images 100 comprises a first means for capturing images 101 and a second means for capturing images. Analog cameras, USB cameras, or Firewire cameras can serve as means for capturing images (paragraph 0090);
a face recognition engine configured to extract features from one or more captured images of the user's face in response to a candidate being presented to the user (Any image-based face detection algorithm can be used to detect human faces from an input image frame 330. Typically, a machine learning-based face detection algorithm is employed. The face detection algorithm produces a face window 366 that corresponds to the locations and the sizes of the detected face. The face localization 380 step estimates the two-dimensional and three-dimensional poses of the face to normalize the face to a localized facial image 384, where each facial feature is localized within a standard facial feature window 406. The facial feature localization 410 then finds the accurate locations of each facial feature or transient feature to extract them in a facial feature window 403 or a transient feature window 440 (paragraph 0067);
Moon et al fails to teach a matching engine configured to assign a satisfaction value to the extracted features, the satisfaction value representing the user's satisfaction with the presented candidate; and
wherein the matching engine is configured to select, for presentation, one or more further candidates dependent on satisfaction values assigned with reference to candidates presented to the user so far.
Sung et al teaches a matching engine configured to assign a satisfaction value to the extracted features, the satisfaction value representing the user's satisfaction with the presented candidate (face retrieval unit 10 compares the facial images stored in the face DB 11 and an input facial image using a predetermined face retrieval algorithm and calculates confidence values (satisfaction value) of the stored facial images according to their similarity with the input facial image in operation 21. The face retrieval unit 10 may use, by way of a non-limiting example, a component-based linear discriminant analysis (LDA) algorithm. Such a component-based LDA algorithm classifies a facial image according to facial components such as a forehead, eyebrows, a nose, cheeks, and a mouth, and expresses each image as vectors for the classified components (paragraph 0024); and
wherein the matching engine is configured to select, for presentation, one or more further candidates dependent on satisfaction values assigned with reference to candidates presented to the user so far (rank determinator 121 ranks of facial images of the face DB 11 with reference to the confidence values (satisfaction values) calculated by the face retrieval unit 10 (paragraph 0026). candidate determinator 122 determines K images as candidate images in the determined rank order (candidates dependent on satisfaction values that were assigned) and obtains IDs corresponding to the K candidate images with reference to the information stored in the face DB 11 in operation 22. The value K, for example, may be limited to the number of images capable of being displayed on a screen or selected by a user (paragraph 0027).
Therefore, it would have been obvious to a person of ordinary skill in the art to modify Moon et al to include: a matching engine configured to assign a satisfaction value to the extracted features, the satisfaction value representing the user's satisfaction with the presented candidate; and
wherein the matching engine is configured to select, for presentation, one or more further candidates dependent on satisfaction values assigned with reference to candidates presented to the user so far.
The reason for doing so would be to accurately identify image by ranking desired features.
Regarding claim 51, Moon et al in view of Sung et al teaches wherein the face recognition engine comprises a feature extractor trained to extract facial characteristics, wherein the extracted features are provided as a feature vector comparable to feature vectors generated for other captured images, preferably wherein the facial characteristics include one or more of gender, age, facial landmarks, facial expression (Moon et al: A given facial feature image 642 inside the standard facial feature window 406 is fed to the trained learning machines, and then each machine outputs the responses 813 to the particular pose vector 462. The pose vector represents the difference in position, scale, and orientation that the given facial feature image has against the standard feature positions and sizes. The pose vector is used to correctly extract the facial features and the transient features (paragraph 0075).
Regarding claim 54, Moon et al in view of Sung et al teaches wherein the matching engine is configured to compare the feature vector with one or more other feature vectors to obtain one or more relative quantities, wherein the matching engine is configured to estimate the satisfaction value dependent on the one or more relative quantities (Sung et al: performing a face retrieval for an input facial image with reference to the stored facial images and calculating confidence values of the stored facial images; determining candidates corresponding to a predetermined number of facial images, which are selected among the stored facial images on the basis of the confidence values; and comparing feature vectors of the input facial image with feature vectors of each candidate one by one and recognizing the input facial image (paragraph 0010).
Therefore, it would have been obvious to a person of ordinary skill in the art to modify Moon et al to include: wherein the matching engine is configured to compare the feature vector with one or more other feature vectors to obtain one or more relative quantities, wherein the matching engine is configured to estimate the satisfaction value dependent on the one or more relative quantities.
The reason for doing so would be to rank the extracted features by comparing the extracted features to reference features.
Regarding claim 55, Moon et al in view of Sung et al teaches wherein the matching engine is configured to select the one or more further candidates by way of: selecting at least one candidate out of the candidates presented so far subject to the corresponding satisfaction values, selecting the one or more further candidates based on a similarity measure between the at least one selected candidate and other candidates not presented yet, preferably wherein the at least one selected candidate is the candidate with the highest satisfaction value (Sung et al: rank determinator 121 determines ranks of the facial images based on the confidence values, and the candidate determinator 122 displays K images in rank order on the screen as shown by numeral 31. As FIG. 3 illustrates, facial images of a registered person resembling the input facial image are more likely to be included than the facial images of other persons in a high confidence value order (paragraph 0028 and fig 3).
Therefore, it would have been obvious to a person of ordinary skill in the art to modify Moon et al to include: wherein the matching engine is configured to select the one or more further candidates by way of: selecting at least one candidate out of the candidates presented so far subject to the corresponding satisfaction values, selecting the one or more further candidates based on a similarity measure between the at least one selected candidate and other candidates not presented yet, preferably wherein the at least one selected candidate is the candidate with the highest satisfaction value.
The reason for doing so would be to rank the candidate image similar to reference image.
Regarding claim 56, Moon et al teaches a pattern recognition engine for extracting features from the pictures or videos of the candidates (facial image processing, from face detection and tracking 370 to face localization 380, and to facial feature localization 410. Any image-based face detection algorithm can be used to detect human faces from an input image frame 330. (paragraph 0067), wherein the pattern recognition engine is configured to extract features from the pictures or videos of the other candidates thereby generating corresponding candidate feature vectors, wherein the pattern recognition engine is configured to extract features from the picture or video of the at least one selected candidate thereby generating a corresponding reference candidate feature vector (Once the emotion-sensitive feature vector 962 has been computed from the input facial image 630, they are fed to the facial muscle actions recognition machine 953 to estimate the likelihood of the facial image having each of the muscle actions (paragraph 0078),
Moon et al fails to teach wherein the matching engine is configured to compare the reference candidate feature vector with the candidate feature vectors to obtain one or more relative quantities, and
wherein the matching engine is configured to select the one or more further candidates subject to the one or more relative quantities, preferably according to one or more of the highest or lowest one or more relative quantities, preferably wherein the matching engine is configured to output at least the candidate with the highest satisfaction value,
Sung et al teaches wherein the matching engine is configured to compare the reference candidate feature vector with the candidate feature vectors to obtain one or more relative quantities (candidate image selection unit 12 (matching engine) includes a rank determinator 121 and a candidate determinator 122 (paragraph 0020). Confidence values indicating a similarity (compare) between the obtained LDA feature vectors and LDA feature vectors of each facial image stored in the face DB 11 are calculated (paragraph 0025)., and
wherein the matching engine is configured to select the one or more further candidates subject to the one or more relative quantities, preferably according to one or more of the highest or lowest one or more relative quantities, preferably wherein the matching engine is configured to output at least the candidate with the highest satisfaction value (candidate image selection unit 12 (matching engine) includes a rank determinator 121 and a candidate determinator 122 (paragraph 0020). Confidence values indicating a similarity between the obtained LDA feature vectors and LDA feature vectors of each facial image stored in the face DB 11 are calculated (paragraph 0025). The rank determinator 121 ranks of facial images of the face DB 11 with reference to the confidence values calculated by the face retrieval unit 10 (paragraph 0026). The candidate determinator 122 determines K images as candidate images in the determined rank order and obtains IDs corresponding to the K candidate images with reference to the information stored in the face DB 11 in operation 22. The value K, for example, may be limited to the number of images capable of being displayed on a screen or selected by a user (paragraph 0027).
Therefore, it would have been obvious to a person of ordinary skill in the art to modify Moon et al to include: wherein the matching engine is configured to compare the reference candidate feature vector with the candidate feature vectors to obtain one or more relative quantities, and
wherein the matching engine is configured to select the one or more further candidates subject to the one or more relative quantities, preferably according to one or more of the highest or lowest one or more relative quantities, preferably wherein the matching engine is configured to output at least the candidate with the highest satisfaction value.
The reason for doing so would be to rank the candidate image similar to reference image.
Regarding claim 57, Moon et al teaches A computer implemented method for assisting a user in identifying preferences with respect to different candidates presented to the user (fig. 1), comprising:
presenting a candidate to the user;
capturing one or more images of the face of the user while the candidate is presented to the user (means for capturing images 100 is placed near the media display 152, so that it can capture the faces of media audience 790 watching the display (paragraph 0064). means for capturing images 100 comprises a first means for capturing images 101 and a second means for capturing images. Analog cameras, USB cameras, or Firewire cameras can serve as means for capturing images (paragraph 0090);
extracting features from the one or more captured images of the user's face (Any image-based face detection algorithm can be used to detect human faces from an input image frame 330. Typically, a machine learning-based face detection algorithm is employed. The face detection algorithm produces a face window 366 that corresponds to the locations and the sizes of the detected face. The face localization 380 step estimates the two-dimensional and three-dimensional poses of the face to normalize the face to a localized facial image 384, where each facial feature is localized within a standard facial feature window 406. The facial feature localization 410 then finds the accurate locations of each facial feature or transient feature to extract them in a facial feature window 403 or a transient feature window 440 (paragraph 0067),
Moon et al fails to teach assigning a satisfaction value to the extracted features, the satisfaction value representing a user's satisfaction with the presented candidate, selecting, for presentation, one or more further candidates dependent on satisfaction values assigned with reference to candidates presented to the user so far.
Sung et al teaches assigning a satisfaction value to the extracted features, the satisfaction value representing a user's satisfaction with the presented candidate (face retrieval unit 10 compares the facial images stored in the face DB 11 and an input facial image using a predetermined face retrieval algorithm and calculates confidence values (satisfaction value) of the stored facial images according to their similarity with the input facial image in operation 21. The face retrieval unit 10 may use, by way of a non-limiting example, a component-based linear discriminant analysis (LDA) algorithm. Such a component-based LDA algorithm classifies a facial image according to facial components such as a forehead, eyebrows, a nose, cheeks, and a mouth, and expresses each image as vectors for the classified components (paragraph 0024),
selecting, for presentation, one or more further candidates dependent on satisfaction values assigned with reference to candidates presented to the user so far (rank determinator 121 ranks of facial images of the face DB 11 with reference to the confidence values (satisfaction values) calculated by the face retrieval unit 10 (paragraph 0026). candidate determinator 122 determines K images as candidate images in the determined rank order (candidates dependent on satisfaction values that were assigned) and obtains IDs corresponding to the K candidate images with reference to the information stored in the face DB 11 in operation 22. The value K, for example, may be limited to the number of images capable of being displayed on a screen or selected by a user (paragraph 0027).
Therefore, it would have been obvious to a person of ordinary skill in the art to modify Moon et al to include: assigning a satisfaction value to the extracted features, the satisfaction value representing a user's satisfaction with the presented candidate, selecting, for presentation, one or more further candidates dependent on satisfaction values assigned with reference to candidates presented to the user so far.
The reason for doing so would be to select the closest image desired based on user preference.
Regarding claim 58, Moon et al teaches comprising:
extracting quantifiable features first from the image/s resulting in a first feature vector (the emotion-sensitive feature extraction 966 step computes the emotion-sensitive features 961 from the localized facial and transient features (paragraph 0063). (Any image-based face detection algorithm can be used to detect human faces from an input image frame 330. Typically, a machine learning-based face detection algorithm is employed. The face detection algorithm produces a face window 366 that corresponds to the locations and the sizes of the detected face. The face localization 380 step estimates the two-dimensional and three-dimensional poses of the face to normalize the face to a localized facial image 384, where each facial feature is localized within a standard facial feature window 406. The facial feature localization 410 then finds the accurate locations of each facial feature or transient feature to extract them in a facial feature window 403 or a transient feature window 440 (paragraph 0067);
Moon et al fails to teach subsequently extracting other features from the image/s subject to the extracted quantifiable features, resulting in a second feature vector;
combining first and second feature vectors into a feature vector assigned to the image/s; and
storing the feature vector in a data structure, preferably in combination with one or more of:
the one or more images underlying the feature vector, the picture or the video or an identifier for the associate candidate, and the assigned satisfaction value.
Sung et al teaches subsequently extracting other features from the image/s subject to the extracted quantifiable features, resulting in a second feature vector (face retrieval unit 10 divides an input image into facial components, operates vectors representing the divided components with the LDA matrices corresponding to the divided components, and obtains LDA feature vectors. Confidence values indicating a similarity between the obtained LDA feature vectors (first feature vector) and LDA feature vectors of each facial image (second feature vector) stored in the face DB 11 are calculated (paragraph 0025);
combining first and second feature vectors into a feature vector assigned to the image/s (Sung et al: face retrieval unit 10 divides an input image into facial components, operates vectors representing the divided components with the LDA matrices corresponding to the divided components, and obtains LDA feature vectors (paragraph 0025); and
storing the feature vector in a data structure (LDA feature vectors and LDA feature vectors of each facial image stored in the face DB 11 (paragraph 0025), preferably in combination with one or more of:
the one or more images underlying the feature vector, the picture or the video or an identifier for the associate candidate, and the assigned satisfaction value (The learning DB 14 stores parameters composing a hyper plane in the feature vector space allowing each person registered in the face DB 11 to be discriminated from other registered persons by using feature vectors obtained by components of a plurality of facial images corresponding to each registered person. The number of SVM classifiers is the same as the number of registered persons in the face DB 11. Therefore, there is obtained a similarity determining whether feature vectors of the input image are in a subspace of each person whose ID is determined as a candidate by the candidate determinator 122 using an SVM classifier. (paragraph 0030).
Therefore, it would have been obvious to a person of ordinary skill in the art to modify Moon et al to include: subsequently extracting other features from the image/s subject to the extracted quantifiable features, resulting in a second feature vector;
combining first and second feature vectors into a feature vector assigned to the image/s; and
storing the feature vector in a data structure, preferably in combination with one or more of:
the one or more images underlying the feature vector, the picture or the video or an identifier for the associate candidate, and the assigned satisfaction value.
The reason for doing so would be to select desired image features and rank the image features.
Regarding claim 60, Moon et al in view of Sung et al teaches capturing one or more reference images of the user's face while no candidate is presented to the user (Moon et al: means for capturing images 100 is placed near the media display 152, so that it can capture the faces of media audience 790 watching the display (paragraph 0064).;
extracting reference features from the one or more captured reference images of the user's face, and generating a reference feature vector from the extracted reference features comparable to feature vectors generated for other captured images (Moon et al: A given facial feature image 642 inside the standard facial feature window 406 is fed to the trained learning machines, and then each machine outputs the responses 813 to the particular pose vector 462. The pose vector represents the difference in position, scale, and orientation that the given facial feature image has against the standard feature positions and sizes. The pose vector is used to correctly extract the facial features and the transient features (paragraph 0075).
.
Regarding claim 61, Moon et al in view of Sung et al teaches wherein the one or more reference images are captured prior to the user being presented any candidate, preferably wherein the candidates are presented to the user on a screen in fixed intervals with a break between two intervals in which break no candidate is shown, preferably wherein one or more additional reference images are captured during such one or more breaks (Moon et al: means for capturing images 100 is placed near the media display 152, so that it can capture the faces of media audience 790 watching the display (paragraph 0064). Note: preferred limitations are not required to meet the limitations of the claim.
Regarding claim 63, Moon et al in view of Sung et al teaches comparing the feature vector with one or more other feature vectors to obtain one or more relative quantities, and estimating the satisfaction value dependent on the one or more relative quantities (Sung et al: performing a face retrieval for an input facial image with reference to the stored facial images and calculating confidence values of the stored facial images; determining candidates corresponding to a predetermined number of facial images, which are selected among the stored facial images on the basis of the confidence values; and comparing feature vectors of the input facial image with feature vectors of each candidate one by one and recognizing the input facial image (paragraph 0010).
Therefore, it would have been obvious to a person of ordinary skill in the art to modify Moon et al to include: comparing the feature vector with one or more other feature vectors to obtain one or more relative quantities, and estimating the satisfaction value dependent on the one or more relative quantities.
The reason for doing so would be to rank a quantity of desired features.
Regarding claim 64, Moon et al in view of Sung et al teaches selecting the one or more further candidates by way of: selecting at least one candidate out of the candidates presented subject to the corresponding satisfaction values, selecting the one or more further candidates based on a similarity measure between the least one selected candidate and other candidates not presented yet, preferably wherein the at least one selected candidate is the candidate with the highest satisfaction value (Sung et al: rank determinator 121 determines ranks of the facial images based on the confidence values, and the candidate determinator 122 displays K images in rank order on the screen as shown by numeral 31. As FIG. 3 illustrates, facial images of a registered person resembling the input facial image are more likely to be included than the facial images of other persons in a high confidence value order (paragraph 0028 and fig 3).
Therefore, it would have been obvious to a person of ordinary skill in the art to modify Moon et al to include: selecting the one or more further candidates by way of: selecting at least one candidate out of the candidates presented subject to the corresponding satisfaction values, selecting the one or more further candidates based on a similarity measure between the least one selected candidate and other candidates not presented yet, preferably wherein the at least one selected candidate is the candidate with the highest satisfaction value.
The reason for doing so would be to ranking an image based on a desired selected image.
Regarding claim 65, Moon et al teaches wherein the candidates of the set are represented by one of human beings, animals, items, text and scenes, or a combination thereof, wherein the candidates are presented to the user in form of pictures or videos on a display (the step derives a set of filters that are matched to facial feature shapes or transient feature (facial wrinkles) shapes, so that the filters can extract the features relevant to facial expressions, and at the same time can ignore other image variations due to lighting and interpersonal variations, etc (paragraph 0040), the method further comprising:
Moon et al fails to teach extracting features from the picture or video of the at least one selected candidate thereby generating a corresponding reference candidate feature vector, extracting features from the pictures or videos of other candidates not presented yet thereby generating corresponding candidate feature vectors, comparing the reference candidate feature vector with the candidate feature vectors to obtain one or more relative quantities, and selecting the one or more further candidates dependent on the one or more relative quantities, preferably selecting the one or more further candidates according to one or more of the highest and lowest one or more relative quantities
Sung et al teaches extracting features from the picture or video of the at least one selected candidate thereby generating a corresponding reference candidate feature vector, extracting features from the pictures or videos of other candidates not presented yet thereby generating corresponding candidate feature vectors, comparing the reference candidate feature vector with the candidate feature vectors to obtain one or more relative quantities, and selecting the one or more further candidates dependent on the one or more relative quantities, preferably selecting the one or more further candidates according to one or more of the highest and lowest one or more relative quantities (candidate image selection unit 12 includes a rank determinator 121 and a candidate determinator 122 (paragraph 0020). Confidence values indicating a similarity between the obtained LDA feature vectors and LDA feature vectors of each facial image stored in the face DB 11 are calculated (paragraph 0025). The rank determinator 121 ranks of facial images of the face DB 11 with reference to the confidence values calculated by the face retrieval unit 10 (paragraph 0026). The candidate determinator 122 determines K images as candidate images in the determined rank order and obtains IDs corresponding to the K candidate images with reference to the information stored in the face DB 11 in operation 22. The value K, for example, may be limited to the number of images capable of being displayed on a screen or selected by a user (paragraph 0027).
Therefore, it would have been obvious to a person of ordinary skill in the art to modify Moon et al to include: extracting features from the picture or video of the at least one selected candidate thereby generating a corresponding reference candidate feature vector, extracting features from the pictures or videos of other candidates not presented yet thereby generating corresponding candidate feature vectors, comparing the reference candidate feature vector with the candidate feature vectors to obtain one or more relative quantities, and selecting the one or more further candidates dependent on the one or more relative quantities, preferably selecting the one or more further candidates according to one or more of the highest and lowest one or more relative quantities.
The reason for doing so would be to ranking an image based on a desired selected image.
Regarding claim 66, Moon et al in view of Sung et al teaches presenting at least the candidate with the highest satisfaction value to the user, preferably wherein any candidates to be presented are presented on a screen, preferably wherein the user browses the candidates suggested on the screen (Sung et al: paragraph 0028 and fig 3).
Therefore, it would have been obvious to a person of ordinary skill in the art to modify Moon et al to include: presenting at least the candidate with the highest satisfaction value to the user, preferably wherein any candidates to be presented are presented on a screen, preferably wherein the user browses the candidates suggested on the screen.
The reason for doing so would be to view the ranked images.
Regarding claim 68, Moon et al teaches A computer implemented method for assisting a user in identifying preferences with respect to different candidates presented to the user (fig. 1), comprising:
sending a picture or video of a candidate to an electronic device of the user (means for capturing images 100 is placed near the media display 152, so that it can capture the faces of media audience 790 watching the display (paragraph 0064). means for capturing images 100 comprises a first means for capturing images 101 and a second means for capturing images. Analog cameras, USB cameras, or Firewire cameras can serve as means for capturing images (paragraph 0090);
receiving one or more images of the user's face from the electronic device captured while the candidate is presented to the user (The means for capturing images 100 is placed near the media display 152, so that it can capture the faces of media audience 790 watching the display. The displayed media content is the visual stimulus in this embodiment, and is controlled by the control and processing system 162. The video feed from the means for capturing images 100 is transferred to the control and processing system 162 via means for video interface 115 (receiving one or more images) (paragraph 0064);
extracting features from the one or more received images (Any image-based face detection algorithm can be used to detect human faces from an input image frame 330. Typically, a machine learning-based face detection algorithm is employed. The face detection algorithm produces a face window 366 that corresponds to the locations and the sizes of the detected face. The face localization 380 step estimates the two-dimensional and three-dimensional poses of the face to normalize the face to a localized facial image 384, where each facial feature is localized within a standard facial feature window 406. The facial feature localization 410 then finds the accurate locations of each facial feature or transient feature to extract them in a facial feature window 403 or a transient feature window 440 (paragraph 0067);
Moon et al fails to teach assigning a satisfaction value to the extracted features, the satisfaction value representing a user's satisfaction with the presented candidate, and sending a request to another server to select, for presentation, one or more further candidates dependent on satisfaction value/s assigned with reference to candidates previously presented to the user
Sung et al teaches assigning a satisfaction value to the extracted features, the satisfaction value representing a user's satisfaction with the presented candidate (face retrieval unit 10 compares the facial images stored in the face DB 11 and an input facial image using a predetermined face retrieval algorithm and calculates confidence values (satisfaction value) of the stored facial images according to their similarity with the input facial image in operation 21. The face retrieval unit 10 may use, by way of a non-limiting example, a component-based linear discriminant analysis (LDA) algorithm. Such a component-based LDA algorithm classifies a facial image according to facial components such as a forehead, eyebrows, a nose, cheeks, and a mouth, and expresses each image as vectors for the classified components (paragraph 0024), and
sending a request to another server to select, for presentation, one or more further candidates dependent on satisfaction value/s assigned with reference to candidates previously presented to the user (rank determinator 121 ranks of facial images of the face DB 11 with reference to the confidence values (satisfaction values) calculated by the face retrieval unit 10 (paragraph 0026). candidate determinator 122 determines K images as candidate images in the determined rank order (candidates dependent on satisfaction values that were assigned) and obtains IDs corresponding to the K candidate images with reference to the information stored in the face DB 11 in operation 22. The value K, for example, may be limited to the number of images capable of being displayed on a screen or selected by a user (paragraph 0027).
Therefore, it would have been obvious to a person of ordinary skill in the art to modify Moon et al to include: assigning a satisfaction value to the extracted features, the satisfaction value representing a user's satisfaction with the presented candidate, and sending a request to another server to select, for presentation, one or more further candidates dependent on satisfaction value/s assigned with reference to candidates previously presented to the user.
The reason for doing so would be to ranked images.
Claim(s) 52 and 59 is/are rejected under 35 U.S.C. 103 as being unpatentable over Moon et al in view of Sung et al US 2005/0117783 further in view Guo et al US 20200302668.
Regarding claim 52, Moon et al teaches wherein the feature extractor comprises:
a first feature extractor module trained to extract quantifiable features from the image/s (the emotion-sensitive feature extraction 966 step computes the emotion-sensitive features 961 from the localized facial and transient features (paragraph 0063), and
Moon et al in view of Sung et al fails to teach a second feature extractor module trained to extract other features from the image/s subject to the quantifiable features extracted by the first feature extractor module,
wherein the second feature extractor module is configured to select, subject to the quantifiable extracted features supplied by the first feature extractor, a model out of a set of models, to be applied for extracting the other features, preferably wherein the quantifiable extracted features include landmarks in the face of the user, preferably wherein the other extracted features include semantic features representing the facial expression of the user.
Guo et al teaches a second feature extractor module trained to extract other features from the image/s subject to the quantifiable features extracted by the first feature extractor module (avatar model includes: extracting a human face feature point from the human face in the image (paragraph 0064),
wherein the second feature extractor module is configured to select, subject to the quantifiable extracted features supplied by the first feature extractor, a model out of a set of models, to be applied for extracting the other features, preferably wherein the quantifiable extracted features include landmarks in the face of the user, preferably wherein the other extracted features include semantic features representing the facial expression of the user (a matched avatar model, that is, the target avatar model, is selected from the avatar model set according to a requirement, a preference, or the like of a user of the terminal (paragraph 0065) Note: preferred limitations are not required to meet this limitation of this claim
Therefore, it would have been obvious to a person of ordinary skill in the art to modify Moon et al in view of Sung et al to include: a second feature extractor module trained to extract other features from the image/s subject to the quantifiable features extracted by the first feature extractor module,
wherein the second feature extractor module is configured to select, subject to the quantifiable extracted features supplied by the first feature extractor, a model out of a set of models, to be applied for extracting the other features, preferably wherein the quantifiable extracted features include landmarks in the face of the user, preferably wherein the other extracted features include semantic features representing the facial expression of the user..
The reason for doing so would be to accurately extract features by selecting a model that accurately extracts desired features of an image.
Regarding claim 59, Moon et al in view of Sung et al teaches all of the limitations of claim 57
Moon et al in view of Sung et al fails to teach comprising: selecting a facial model based on one or more of the extracted quantifiable features, and applying the selected facial model in the subsequent step of extracting the other features, preferably wherein the facial model is a facial model representing an ethnic group the user is identified to belong to based on the one or more extracted quantifiable features.
Guo et al teaches comprising: selecting a facial model based on one or more of the extracted quantifiable features, and applying the selected facial model in the subsequent step of extracting the other features, preferably wherein the facial model is a facial model representing an ethnic group the user is identified to belong to based on the one or more extracted quantifiable features ((avatar model includes: extracting a human face feature point from the human face in the image (paragraph 0064). a matched avatar model, that is, the target avatar model, is selected from the avatar model set according to a requirement, a preference, or the like of a user of the terminal (paragraph 0065) Note: facial model representing an ethnic group is preferred but not required to meet this limitation.
Therefore, it would have been obvious to a person of ordinary skill in the art to modify Moon et al in view of Sung et al to include: comprising: selecting a facial model based on one or more of the extracted quantifiable features, and applying the selected facial model in the subsequent step of extracting the other features, preferably wherein the facial model is a facial model representing an ethnic group the user is identified to belong to based on the one or more extracted quantifiable features.
The reason for doing so would be to accurately extract features by selecting a model that accurately extracts desired features of an image.
Allowable Subject Matter
Claims 53, 62 and 67 are objected to as being dependent upon a rejected base claim, but would be allowable if rewritten in independent form including all of the limitations of the base claim and any intervening claims.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to MICHAEL L BURLESON whose telephone number is (571)272-7460.
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, Akwasi Sarpong can be reached on 571 270-3438 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 Burleson
Patent Examiner
Art Unit 2683
Michael Burleson
July 25, 2026
/MICHAEL BURLESON/
/AKWASI M SARPONG/SPE, Art Unit 2681 7/27/2026
Prosecution Insights