{"search_session":{},"preferences":{"l":"fr","queryLanguage":"fr"},"patentId":"US_8139817_B2","frontPageModel":{"patentViewModel":{"ref":{"entityRefId":"176-827-606-438-751","entityRefType":"PATENT"},"entityMetadata":{"linkedIds":{"empty":true},"tags":[],"collections":[{"id":11867,"type":"PATENT","title":"University of Ottawa Patent Portfolio","description":"","access":"OPEN_ACCESS","displayAvatar":true,"attested":false,"itemCount":955,"tags":[],"user":{"id":91044780,"username":"Cambialens","firstName":"","lastName":"","created":"2015-05-04T00:55:26.000Z","displayName":"Cambialens","preferences":"{\"usage\":\"public\",\"beta\":false}","accountType":"PERSONAL","isOauthOnly":false},"notes":[{"id":8471,"type":"COLLECTION","user":{"id":91044780,"username":"Cambialens","firstName":"","lastName":"","created":"2015-05-04T00:55:26.000Z","displayName":"Cambialens","preferences":"{\"usage\":\"public\",\"beta\":false}","accountType":"PERSONAL","isOauthOnly":false},"text":"
Search Applicants and Owners separately:univ* AND Ottawa. Select more for logical variants. Add to collection. Select all patents in the collection and expand by simple families. Add to collection. Total patents: 876
Search Applicants and Owners separately:univ* AND Ottawa. Select more for logical variants. Add to collection. Select all patents in the collection and expand by simple families. Add to collection. Total patents: 876
acquiring a plurality of frames from the video sequence;\n
detecting a face of an individual within a first frame of the plurality of frames;\n
performing continuous tracking of the face of the individual over the plurality of frames;\n
extracting from the first frame a first face image of the face of the individual;\n
storing the first face image in a face log, the face log for storing face images of the face of the individual;\n
extracting from a second frame of the plurality of frames a second face image of the face of the individual with use of the continuous tracking of the face;\n
determining a first quality score for the first face image, the first quality score based upon assessment of the first face image on the basis of a plurality of criteria;\n
determining a second quality score for the second face image, the second quality score based upon assessment of the second face image on the basis of the plurality of criteria; and\n
performing one of:\n"],"number":1,"annotation":false,"claim":true,"title":false},{"lines":["The method of claim 1 wherein each of the first quality score and the second quality score is a respective weighted sum of scores determined in respect of respectively the first face image and the second face image on the basis of the plurality of criteria."],"number":2,"annotation":false,"claim":true,"title":false},{"lines":["The method of claim 2 wherein the plurality of criteria is selected from a face image characteristic group consisting of: pose estimation; illumination quality criteria; image sharpness; skin content; and image resolution."],"number":3,"annotation":false,"claim":true,"title":false},{"lines":["The method of claim 3 wherein illumination quality criteria for scoring any specific face image further comprises criteria for dynamic range of illumination and evenness of illumination of a face of the specific face image."],"number":4,"annotation":false,"claim":true,"title":false},{"lines":["The method of claim 4 wherein a threshold is associated with each criterion of the plurality of criteria, the threshold used with a score determined in respect of the associated criterion to determine if the associated criterion is utilized in determining the quality score."],"number":5,"annotation":false,"claim":true,"title":false},{"lines":["The method of claim 1 further comprising:\npurging the first face image from the face log and storing the second face image in the face log if the first quality score is below the second quality score and if the second face image is absent from the face log;\npurging the first face image from the face log if the first quality score is below the second quality score and if the second face image is already stored in the face log; and\npurging the first face image from the face log if the first quality score is below a minimum quality score.\n
estimating a group size of a group of individuals in the video sequence;\n
selecting a second plurality of frames from the plurality of frames of the video sequence in which faces of all individuals of the group are visible;\n
for each frame of the second plurality of frames:\n\ndetecting a respective face of each individual of the group;\nextracting from the frame a respective face image of each respective face;\nstoring each respective face image in a respective face log of an individual of the group whose face appears in the respective face image;\ndetermining a respective quality score for each respective face image, the respective quality score based upon assessment of the respective face image on the basis of the plurality of criteria; and\ndetermining from respective quality scores a minimum respective quality score for the respective face images within the frame;\n
determining for all of the frames of the second plurality of frames a highest minimum respective quality score; and\n
purging all respective face images from the respective face logs with respective quality scores below the highest minimum respective quality score and purging all respective face images from the respective face logs with respective quality scores below the minimum quality score."],"number":6,"annotation":false,"claim":true,"title":false},{"lines":["The method of claim 1 wherein purging the face log occurs when according to the continuous tracking of the face of the individual, a video image of the individual exits the plurality of frames from the video sequence."],"number":7,"annotation":false,"claim":true,"title":false},{"lines":["The method of claim 1 wherein purging the face log occurs based upon storage constraints."],"number":8,"annotation":false,"claim":true,"title":false},{"lines":["The method of claim 1 wherein each quality score associated with each face image is stored in the face log in metadata associated with the face image."],"number":9,"annotation":false,"claim":true,"title":false},{"lines":["The method of claim 1 further comprising the steps of:\n
determining a candidate region in each frame of the plurality of frames;\n
tracking the candidate region between frames; and\n
performing face detection on the candidate region."],"number":10,"annotation":false,"claim":true,"title":false},{"lines":["A system for generating person oriented face logs from a video sequence, the system comprising:\n
a face detection module for, within each frame of the video sequence, detecting face of an individual and extracting a first face image of the face of the individual, and for extracting a second face image of the face of the individual;\n
a tracking module for performing continuous tracking of the face of the individual within frames of the video sequence, the second face image of the face of the individual extracted by the face detection module with use of the continuous tracking of the face of the individual performed by the tracking module;\n
a quality analysis module for receiving the first face image and the second face image from the face detection module and for determining a first quality score for the first face image, the first quality score based upon assessment of the first face image on the basis of a plurality of criteria, and for determining a second quality score for the second face image, the second quality score based upon assessment of the second face image on the basis of the plurality of criteria; and\n
a storage device for storing the first face image with the first quality score and the second face image with the second quality score in a face log, the face log for storing face images and quality scores for the face images of the face of the individual, wherein the face log is periodically purged of received face images with performance of one of:\n"],"number":11,"annotation":false,"claim":true,"title":false},{"lines":["The system of claim 11 wherein the tracking module further is for tracking a candidate region between frames of the video sequence and for providing the candidate region to the face detection module."],"number":12,"annotation":false,"claim":true,"title":false},{"lines":["The system of claim 11 wherein the each of the first quality score and the second quality score is generated by a respective weighted sum of scores determined in respect of respectively the first face image and the second face image on the basis of the plurality of criteria."],"number":13,"annotation":false,"claim":true,"title":false},{"lines":["The system of claim 13 wherein the plurality of criteria is selected from an image characteristic group consisting of: pose estimation; illumination quality criteria; image sharpness; skin content; and image resolution."],"number":14,"annotation":false,"claim":true,"title":false},{"lines":["The system of claim 14 wherein illumination quality criteria for scoring any specific face image further comprises criteria for dynamic range of illumination and evenness of illumination of a face of the specific face image."],"number":15,"annotation":false,"claim":true,"title":false},{"lines":["The system of claim 15 wherein a threshold is associated with each criterion of the plurality of criteria, the threshold associated with the criterion used with a score determined in respect of the criterion to determine if the criterion is utilized in determining the quality score."],"number":16,"annotation":false,"claim":true,"title":false},{"lines":["The system of claim 11 wherein purging of the face images is further performed by:\npurging the first face image from the face log and storing the second face image in the face log if the first quality score is below the second quality score and if the second face image is absent from the face log;\npurging the first face image from the face log if the first quality score is below the second quality score and if the second face image is already stored in the face log; and\npurging the first face image from the face log if the first quality score is below a minimum quality score.\n
estimating a group size of a group of individuals in the video sequence;\n
selecting a second plurality of frames from the plurality of frames of the video sequence in which faces of all individuals of the group are visible;\n
for each frame of the second plurality of frames:\n\ndetecting a respective face of each individual of the group;\nextracting from the frame a respective face image of each respective face;\nstoring each respective face image in a respective face log of an individual of the group whose face appears in the respective face image;\ndetermining a respective quality score for each respective face image, the respective quality score based upon assessment of the respective face image on the basis of the plurality of criteria; and\ndetermining from respective quality scores a minimum respective quality score for the respective face images within the frame;\n
determining for all of the frames of the second plurality of frames a highest minimum respective quality score; and\n
purging from the respective face logs all respective face images with respective quality scores below the highest minimum respective quality score and all respective face images with respective quality scores below the minimum quality score."],"number":17,"annotation":false,"claim":true,"title":false},{"lines":["The system of claim 16 wherein purging the face log occurs when according to the tracking of the face of the individual, a video image of the individual exits the plurality of frames from the video sequence."],"number":18,"annotation":false,"claim":true,"title":false},{"lines":["The system of claim 11 wherein each quality score associated with each face image is stored in the face log in metadata associated with the face image."],"number":19,"annotation":false,"claim":true,"title":false},{"lines":["A non-transitory computer readable medium containing instructions for generating person oriented face logs from a video sequence, the instructions which when executed by a processor perform the steps of:\n
acquiring a plurality of frames from the video sequence;\n
detecting a face of an individual within a first frame of the plurality of frames;\n
performing continuous tracking of the face of the individual over the plurality of frames;\n
extracting from the first frame a first face image of the face of the individual;\n
storing the first face image in a face log, the face log for storing face images of the face of the individual;\n
extracting from a second frame of the plurality of frames a second face image of the face of the individual with use of the continuous tracking of the face;\n
determining a first quality score for the first face image, the first quality score based upon assessment of the first face image on the basis of a plurality of criteria;\n
determining a second quality score for the second face image, the second quality score based upon assessment of the second face image on the basis of the plurality of criteria; and\n
performing one of:\n"],"number":20,"annotation":false,"claim":true,"title":false}]}},"filters":{"npl":[],"notNpl":[],"applicant":[],"notApplicant":[],"inventor":[],"notInventor":[],"owner":[],"notOwner":[],"tags":[],"dates":[],"types":[],"notTypes":[],"j":[],"notJ":[],"fj":[],"notFj":[],"classIpcr":[],"notClassIpcr":[],"classNat":[],"notClassNat":[],"classCpc":[],"notClassCpc":[],"so":[],"notSo":[],"sat":[]},"sequenceFilters":{"s":"SEQIDNO","d":"ASCENDING","p":0,"n":10,"sp":[],"si":[],"len":[],"t":[],"loc":[]}}purging the first face image from the face log and storing the second face image in the face log if the first quality score is below the second quality score and if the second face image is absent from the face log;\npurging the first face image from the face log if the first quality score is below the second quality score and if the second face image is already stored in the face log; and\npurging the first face image from the face log if the first quality score is below a minimum quality score.\n