# US 10,311,286 B2 · Fusing ocular-vascular with facial and/or sub-facial information for biometric systems > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 10,311,286 B2 - Document ID: US10311286B2 - Status: Granted - Kind: B2 - Application number: 15/261,224 - Filed: 2016-09-09 - Published: 2017-03-16 - Granted: 2019-06-04 - Earliest claimed: 2015-09-11 - Assignees: EyeVerify Inc. - Applicants: EyeVerify Inc. - Inventors: Sashi K. Saripalle; Vikas Gottemukkula; Reza R. Derakhshani - Web page: https://patentgrep.com/patent/US10311286B2 ## CPC - G06V 40/168: {Feature extraction; Face representation} - G06V 10/751: {Comparing pixel values or logical combinations thereof, or feature values having positional relevance, e.g. template matching} - G06V 10/993: {Evaluation of the quality of the acquired pattern} - G06V 40/161: {Detection; Localisation; Normalisation} - G06V 40/172: {Classification, e.g. identification} - G06V 40/197: {Matching; Classification} - G06V 10/467: {Encoded features or binary features, e.g. local binary patterns [LBP]} - G06V 10/50: by performing operations within image blocks; by using histograms, e.g. histogram of oriented gradients [HoG]; by summing image-intensity values; Projection analysis - G06V 10/56: relating to colour - G06V 40/193: {Preprocessing; Feature extraction} - G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING ## Abstract Biometric enrollment and verification techniques for ocular-vascular, periocular, and facial regions are described. Periocular image regions can be defined based on the dimensions of an ocular region identified in an image of a facial region. Feature descriptors can be generated for interest points in the ocular and periocular regions using a combination of patterned histogram feature descriptors. Quality metrics for the regions can be determined based on region value scores calculated based on texture surrounding the interest points. A biometric matching process for calculating a match score based on the ocular and periocular regions can progressively include additional periocular regions to obtain a greater match confidence. ## Claims ### Claim 1 A computer-implemented method comprising: receiving an image of a facial region of a user, the facial region including an eye and an area surrounding the eye; processing the image to define an ocular image region including at least a portion of the eye in the image of the facial region, wherein the at least a portion of the eye comprises a scleral region of the eye; defining a plurality of periocular image regions each including at least a portion of the area surrounding the eye in the image of the facial region, wherein each of the periocular image regions is sized differently from the ocular image region, and wherein defining a particular one of the periocular image regions comprises: calculating a region height by multiplying a height of the ocular image region including the scleral region with a first numerical factor; calculating a region width by multiplying a width of the ocular image region including the scleral region with a second numerical factor; setting a height of the particular periocular image region equal to the calculated region height; and setting a width of the particular periocular image region equal to the calculated region width; calculating one or more biometric match scores based on the ocular image region and at least one of the periocular regions; and designating the image of the facial region as authentic or not authentic based on the one or more biometric match scores. ### Claim 2 (depends on 1) The method of claim 1, wherein the plurality of periocular image regions comprises at least four periocular image regions. ### Claim 3 (depends on 2) The method of claim 2, wherein the at least four periocular image regions comprise a lower periocular image region disposed below the ocular image region, a right periocular image region disposed to a right of the ocular image region, a periocular image region disposed to a left of the ocular image region, and a periocular image region disposed above the ocular image region. ### Claim 4 (depends on 1) The method of claim 1, wherein defining the plurality of periocular image regions comprises defining a right periocular image region disposed to the right of the ocular image region, the right periocular image region having a width in a range of 10% to 80% of a width of the ocular image region and a height in a range of 120% to 550% of a height of the ocular image region. ### Claim 5 (depends on 1) The method of claim 1, wherein defining the plurality of periocular image regions comprises defining a left periocular image region disposed to a left of the ocular image region, the left periocular image region having a width in a range of 10% to 50% of a width of the ocular image region and a height in a range of 120% to 550% of a height of the ocular image region. ### Claim 6 (depends on 1) The method of claim 1, wherein calculating the one or more biometric match scores comprises: calculating a first biometric match score based on the ocular image region and an ocular enrollment template; and in response to determining that the first biometric match score does not meet a first match threshold, calculating a second biometric match score based on the ocular image region, a first one of the periocular image regions, the ocular enrollment template, and a periocular enrollment template. ### Claim 7 (depends on 6) The method of claim 6, wherein calculating the one or more biometric match scores further comprises, in response to determining that the second biometric match score does not meet a second match threshold, calculating one or more further biometric match scores by iteratively including additional ones of the periocular image regions in calculating the further biometric match scores until either a particular further biometric match score meets a corresponding match threshold or no further periocular image regions are available for inclusion. ### Claim 8 (depends on 7) The method of claim 7, wherein the plurality of periocular image regions are ranked based at least on discriminative power and/or quality, and wherein the additional periocular image regions are iteratively included based on the respective rankings of the additional periocular image regions. ### Claim 9 (depends on 7) The method of claim 7, further comprising dividing one or more of the plurality of periocular image regions into sub-regions based on one or more facial features derived from the periocular image regions, wherein the additional periocular image regions are iteratively included based on cluster importance or the respective rankings of the additional periocular image regions. ### Claim 10 (depends on 1) The method of claim 1, wherein calculating the one or more biometric match scores comprises: identifying a first set of pairs of matched points based on the ocular image region and an enrollment template; and identifying a second set of pairs of matched points based on at least one of the periocular image regions and the enrollment template. ### Claim 11 (depends on 10) The method of claim 10, wherein calculating the one or more biometric match scores further comprises: determining one or more inlier matched points by inputting a combination of the first and second sets of pairs of matched points into an outlier detection algorithm; determining that a number of the inlier matched points that correspond to the ocular image region meets a minimum ocular inlier count; and calculating one of the biometric match scores based at least in part on the inlier matched points. ### Claim 12 (depends on 11) The method of claim 11, wherein the minimum ocular inlier count is equal to 3. ### Claim 13 (depends on 10) The method of claim 10, wherein calculating the one or more biometric match scores further comprises: determining one or more first inlier matched points by inputting the first set of pairs of matched points into an outlier detection algorithm; determining one or more second inlier matched points by inputting the second set of pairs of matched points into the outlier detection algorithm; and calculating one of the biometric match scores based at least in part on an output of the outlier detection algorithm using a combination of the first and second inlier matched points as input. ### Claim 14 (depends on 13) The method of claim 13, wherein calculating the one or more biometric match scores further comprises determining that a number of inlier matched points, obtained from the output of the outlier detection algorithm, that correspond to the ocular image region meets a minimum ocular inlier count. ### Claim 15 (depends on 14) The method of claim 14, wherein the minimum ocular inlier count is equal to 3. ### Claim 16 A system comprising: at least one memory for storing computer-executable instructions; and at least one processing unit for executing the instructions stored on the at least one memory, wherein execution of the instructions programs the at least one processing unit to perform operations comprising: receiving an image of a facial region of a user, the facial region including an eye and an area surrounding the eye; processing the image to define an ocular image region including at least a portion of the eye in the image of the facial region, wherein the at least a portion of the eye comprises a scleral region of the eye; defining a plurality of periocular image regions each including at least a portion of the area surrounding the eye in the image of the facial region, wherein each of the periocular image regions is sized differently from the ocular image region, and wherein defining a particular one of the periocular image regions comprises: calculating a region height by multiplying a height of the ocular image region including the scleral region with a first numerical factor; calculating a region width by multiplying a width of the ocular image region including the scleral region with a second numerical factor; setting a height of the particular periocular image region equal to the calculated region height; and setting a width of the particular periocular image region equal to the calculated region width; calculating one or more biometric match scores based on the ocular image region and at least one of the periocular regions; and designating the image of the facial region as authentic or not authentic based on the one or more biometric match scores. ### Claim 17 (depends on 16) The system of claim 16, wherein the plurality of periocular image regions comprises at least four periocular image regions. ### Claim 18 (depends on 17) The system of claim 17, wherein the at least four periocular image regions comprise a lower periocular image region disposed below the ocular image region, a right periocular image region disposed to a right of the ocular image region, a periocular image region disposed to a left of the ocular image region, and a periocular image region disposed above the ocular image region. ### Claim 19 (depends on 16) The system of claim 16, wherein defining the plurality of periocular image regions comprises defining a right periocular image region disposed to a right of the ocular image region, the right periocular image region having a width in a range of 10% to 80% of a width of the ocular image region and a height in a range of 120% to 550% of a height of the ocular image region. ### Claim 20 (depends on 16) The system of claim 16, wherein defining the plurality of periocular image regions comprises defining a left periocular image region disposed to a left of the ocular image region, the left periocular image region having a width in a range of 10% to 50% of a width of the ocular image region and a height in a range of 120% to 550% of a height of the ocular image region. ### Claim 21 (depends on 16) The system of claim 16, wherein calculating the one or more biometric match scores comprises: calculating a first biometric match score based on the ocular image region and an ocular enrollment template; and in response to determining that the first biometric match score does not meet a first match threshold, calculating a second biometric match score based on the ocular image region, a first one of the periocular image regions, the ocular enrollment template, and a periocular enrollment template. ### Claim 22 (depends on 21) The system of claim 21, wherein calculating the one or more biometric match scores further comprises, in response to determining that the second biometric match score does not meet a second match threshold, calculating one or more further biometric match scores by iteratively including additional ones of the periocular image regions in calculating the further biometric match scores until either a particular further biometric match score meets a corresponding match threshold or no further periocular image regions are available for inclusion. ### Claim 23 (depends on 22) The system of claim 22, wherein the plurality of periocular image regions are ranked based at least on discriminative power and/or quality, and wherein the additional periocular image regions are iteratively included based on the respective rankings of the additional periocular image regions. ### Claim 24 (depends on 22) The system of claim 22, wherein the operations further comprise dividing one or more of the plurality of periocular image regions into sub-regions based on one or more facial features derived from the periocular image regions, wherein the additional periocular image regions are iteratively included based on cluster importance or the respective rankings of the additional periocular image regions. ### Claim 25 (depends on 16) The system of claim 16, wherein calculating the one or more biometric match scores comprises: identifying a first set of pairs of matched points based on the ocular image region and an enrollment template; and identifying a second set of pairs of matched points based on at least one of the periocular image regions and the enrollment template. ### Claim 26 (depends on 25) The system of claim 25, wherein calculating the one or more biometric match scores further comprises: determining one or more inlier matched points by inputting a combination of the first and second sets of pairs of matched points into an outlier detection algorithm; determining that a number of the inlier matched points that correspond to the ocular image region meets a minimum ocular inlier count; and calculating one of the biometric match scores based at least in part on the inlier matched points.