发明名称 Identifying images using face recognition
摘要 A method includes identifying a named entity, retrieving images associated with the named entity, and using a face detection algorithm to perform face detection on the retrieved images to detect faces in the retrieved images. At least one representative face image from the retrieved images is identified, and the representative face image is used to identify one or more additional images representing the at least one named entity.
申请公布号 US9053357(B2) 申请公布日期 2015.06.09
申请号 US201113324058 申请日期 2011.12.13
申请人 Google Inc. 发明人 Yagnik Jay
分类号 G06K9/46;G06K9/00;G06F17/30 主分类号 G06K9/46
代理机构 Fish & Richardson P.C. 代理人 Fish & Richardson P.C.
主权项 1. A method, comprising: identifying at least one named entity; retrieving a set of three or more images associated with the at least one named entity, each of the images in the set including a textual description of the image derived from metadata specific to only that image, wherein the textual description of the image includes at least a portion of a name of the named entity; performing face detection on the retrieved images to detect faces in the retrieved images, wherein the face detection is performed using a face detection algorithm; identifying a representative face image from the retrieved images by comparing each detected face to each of the other detected faces to identify faces that match the representative face image associated with the at least one named entity; determining a number of faces that match the representative face image; comparing the determined number of faces that match the representative face image to a threshold value; determining that the determined number of faces that match the representative face image satisfies the threshold value; in response to determining that the determined number of faces that match the representative face image satisfies the threshold value, building a face model using the representative face image including identifying a training set that includes the representative face image and all other images that match the representative face image from the set of three or more images; and using the face model to identify one or more additional images representing the at least one named entity from images not included in the set.
地址 Mountain View CA US