发明名称 Apparatus and method of determining facial expression type
摘要 A method of determining a facial expression type may include extracting feature points representing facial characteristics from a facial image of a user; grouping the extracted feature points into a plurality of regions; and determining a facial expression type for each of a plurality of groups using feature points and a facial expression type function corresponding to each of the groups.
申请公布号 US9355304(B2) 申请公布日期 2016.05.31
申请号 US201414553972 申请日期 2014.11.25
申请人 KOREA INSTITUTE OF ORIENTAL MEDICINE 发明人 Do Jun Hyeong;Nam Ji Ho;Jang Jun Su;Lee Si Woo;So Ji Ho;Kim Na Hye;Kim Jong Yeol
分类号 G06K9/00 主分类号 G06K9/00
代理机构 McDermott Will & Emery LLP 代理人 McDermott Will & Emery LLP
主权项 1. A computer-implemented method of determining a facial expression type, the method comprising: extracting feature points representing facial characteristics from a facial image of a user; grouping the extracted feature points into a plurality of groups based at least in part on a plurality of regions; and determining, by at least one processor, a facial expression type for each of the plurality of groups of the extracted feature points by applying the extracted feature points to a facial expression type function corresponding to each of the plurality of groups of the extracted feature points, wherein the determining of the facial expression type for each of the plurality of groups comprises: receiving an input of age information on the user; calibrating the facial expression type function on a basis of the age information; and determining the facial expression type for each of the plurality of groups using the calibrated facial expression type function, and wherein the calibrating of the facial expression type function comprises: dividing the age information into predetermined age groups; calculating widths and lengths of the respective regions using the feature points; calculating averages and standard deviations of the widths and lengths of the respective regions in the divided age groups; and calibrating the facial expression type function using the averages and standard deviations.
地址 Daejeon KR