# US 10,482,317 B2 · Image analysis for determining characteristics of humans > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 10,482,317 B2 - Document ID: US10482317B2 - Status: Granted - Kind: B2 - Application number: 13/467,889 - Filed: 2012-05-09 - Published: 2012-11-15 - Granted: 2019-11-19 - Earliest claimed: 2011-05-09 - Applicants: Catherine Grace McVey - Inventors: Catherine Grace McVey - Web page: https://patentgrep.com/patent/US10482317B2 ## CPC - G06T 7/0014: {using an image reference approach} - A01K 29/00: Other apparatus for animal husbandry - A01K 29/005: {Monitoring or measuring activity} - G06V 10/42: Global feature extraction by analysis of the whole pattern, e.g. using frequency domain transformations or autocorrelation - G06V 40/171: {Local features and components; Facial parts (eye characteristics G06V40/18); Occluding parts, e.g. glasses; Geometrical relationships} - G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL - A01K: ANIMAL HUSBANDRY; AVICULTURE; APICULTURE; PISCICULTURE; FISHING; REARING OR BREEDING ANIMALS, NOT OTHERWISE PROVIDED FOR; NEW BREEDS OF ANIMALS - G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING ## Abstract Systems and methods are disclosed for predicting one or more characteristics of a animal by applying computational methods to image(s) of the animal to generate one or more metrics indicative of the characteristics. Embodiments determine predictors of characteristics by creating a sample library of animals of a particular type, determining facial descriptor measurements for each animal, determining relationships between facial descriptor measurements and additional library data, and selecting predictors from these relationships. Other embodiments predict characteristics of animals not in the library and, optionally, categorize animals for particular discipline, training, management, care, etc. based on the characteristics. Other embodiments predict characteristics and determine strategies for group(s) of animals using predicted characteristics of individual animals. Embodiments are broadly applicable to domesticated animals including dogs, cats, cattle, oxen, llamas, sheep, goats, camels, geese, horses, chickens, turkeys, and pigs. Other embodiments predict certain characteristics of humans, including certain cognitive or developmental disorders. ## Claims ### Claim 1 A computerized method for predicting one or more characteristics of a human based on one or more digital images representing the human, comprising: receiving the one or more digital images representing the human, wherein a portion of at least one of the digital images representing the human's head is annotated with a plurality of reference points; associating at least one other data value about the human with the one or more digital images representing the human; computing, with a digital computer: a plurality of scale-free metrics comprising at least two of the following: a length metric, an area metric, and curvature measures using relative locations of a predetermined subset of the reference points and descriptive points, wherein the descriptive points are based on the relative locations of the reference points; a combined metric based on a predetermined function of the plurality of scale-free metrics; selecting, using dimension reduction techniques, a combination of the plurality of scale-free metrics useable for predicting a characteristic of the human based on the combined metric and data about a group of subjects; and providing the predicted characteristic to an output device. ### Claim 2 (depends on 1) The computerized method of claim 1, further comprising: storing the one or more digital images in a memory operably connected to the digital computer; and annotating the portion of at least one of the digital images representing the human's head with the plurality of reference points. ### Claim 3 (depends on 1) The computerized method of claim 1, wherein the predetermined function is determined based on data relating to a plurality of other humans. ### Claim 4 (depends on 1) The computerized method of claim 1, wherein the predicted characteristic relates to a developmental disorder. ### Claim 5 (depends on 1) The computerized method of claim 1 wherein the predicted characteristic comprises a rating on a childhood autism rating scale. ### Claim 6 (depends on 1) The computerized method of claim 1, wherein the predicted characteristic relates to athletic performance. ### Claim 7 (depends on 1) The computerized method of claim 1 wherein one or more of the plurality of scale-free metrics are computed as z-scores. ### Claim 8 (depends on 1) The computerized method of claim 1, wherein the predicted characteristic relates to one or more of a) type of sporting event most suitable for the human, and b) the expected performance of the human in a particular position on a sports team. ### Claim 9 (depends on 1) The computerized method of claim 1, wherein the human is physically or mentally disabled. ### Claim 10 (depends on 1) The computerized method of claim 1, wherein the predicted characteristic is further based on at least one of: a) additional information related to the human; and b) information related to training the human has completed; and c) information relating to the human's environment or situation. ### Claim 11 (depends on 1) The computerized method of claim 1, wherein at least one of the at least two measures of the plurality of scale-free metrics comprises reference points related to the human's eyes. ### Claim 12 (depends on 1) The computerized method of claim 1, wherein the plurality of scale-free metrics comprises two or more of the following: Eye Depth Proportion, Eye Height Proportion, Eye Length-to-Height Proportion, Mid-Face Width Proportion, Upper Eyelid Proportion, Eye Roundness Proportion, Philtrum Definition Proportion, Upper Lip Thickness Proportion, Lower Lip Thickness Proportion, and Philtrum Length Proportion. ### Claim 13 (depends on 1) The computerized method of claim 1, wherein providing the predicted characteristic to an output device comprises displaying the predicted characteristic. ### Claim 14 A computerized system for predicting one or more characteristics of a human based on one or more digital images representing the human, comprising: at least one memory storing computer-executable instructions and the one or more digital images representing the human; a processor in communication with the at least one memory, executing the stored instructions, causing the processor to: receive the one or more digital images representing the human, wherein a portion of at least one of the digital images representing the human's head is annotated with a plurality of reference points; associate at least one other data value about the human with the one or more digital images representing the human; compute a plurality of scale-free metrics comprising at least two of the following: a length metric, an area metric, and curvature measures using relative locations of a predetermined subset of the reference points and descriptive points, wherein the descriptive points are based on the relative locations of the reference points; compute a combined metric based on a predetermined function of the plurality of scale-free metrics; select, using dimension reduction techniques, a combination of the plurality of scale-free metrics useable for predicting a characteristic of the human based on the combined metric and data about a group of humans; and provide the predicted characteristic to an output device. ### Claim 15 (depends on 14) The computerized system of claim 14, wherein the predicted characteristic relates to a developmental disorder. ### Claim 16 (depends on 14) The computerized system of claim 14, wherein the predicted characteristic comprises a rating on a childhood autism rating scale. ### Claim 17 (depends on 14) The computerized system of claim 14, wherein the predicted characteristic relates to athletic performance. ### Claim 18 A non-transitory, computer-readable medium comprising a set of instructions that, when executed by a computing device, causes the computing device to: receive one or more digital images representing a human, wherein a portion of at least one of the digital images representing the human's head is annotated with a plurality of reference points; associate at least one other data value about the human with the one or more digital images representing the human; compute a plurality of scale-free metrics comprising at least two of the following: a length metric, an area metric, and curvature measures using relative locations of a predetermined subset of the reference points and descriptive points, wherein the descriptive points are based on the relative locations of the reference points; compute a combined metric based on a predetermined function of the plurality of scale-free metrics; select, using dimension reduction techniques, a combination of the plurality of scale-free metrics useable for predicting a characteristic of the human based on the combined metric and data about a group of humans; and provide the predicted characteristic to an output device. ### Claim 19 (depends on 18) The non-transitory, computer-readable medium of claim 18, wherein the predicted characteristic relates to a developmental disorder. ### Claim 20 (depends on 18) The non-transitory, computer-readable medium of claim 18, wherein the predicted characteristic comprises a rating on a childhood autism rating scale. ### Claim 21 (depends on 18) The non-transitory, computer-readable medium of claim 18, wherein the predicted characteristic relates to athletic performance.