发明名称 Systems and methods for identifying a user's demographic characteristics based on the user's social media photographs
摘要 A method identifies user demographic characteristics, such as age and gender. First, a plurality of photos are acquired from postings to a social media site by a specific user. A plurality of facial images are identified in the acquired photos. Using a selected subset of the facial images, the method estimates one or more demographic characteristics of the user. In some cases, the estimation uses a profile photograph of the user. In some cases, the facial images are clustered based on similarity. The cluster that most closely matches the profile photo is used for demographic analysis to estimate the characteristics of the user. In some cases, a cluster is selected based on cluster purity, and the images in the cluster are used to estimate the characteristics of the user. In some cases, other self-portrait features are used, such as large facial images or arms along the perimeter of photographs.
申请公布号 US9589205(B2) 申请公布日期 2017.03.07
申请号 US201414279184 申请日期 2014.05.15
申请人 FUJI XEROX CO., LTD. 发明人 Joshi Dhiraj;Chen Francine;Wilcox Lynn Donelle
分类号 G06K9/00;G06K9/46;G06F17/30;G06K9/52;G06Q50/00 主分类号 G06K9/00
代理机构 Morgan, Lewis & Bockius LLP 代理人 Morgan, Lewis & Bockius LLP
主权项 1. A method of identifying user demographic characteristics, comprising: at a computing device with one or more processors, and memory storing one or more programs for execution by the one or more processors: acquiring a plurality of photos posted to a social media site by a user;identifying a plurality of facial images in the acquired photos;inferring that each of a subset of the plurality of photos is a respective self-potrait taken by a respective person corresponding to a respective facial image in the respective photo, wherein each inference is based on a respective image of the respective person's arm along the perimeter of the respective photo;selecting a subset of facial images from the plurality of facial images, including selecting one or more of the facial images based on their presence in one or more of the inferred self-portraits, wherein selecting the subset of facial images comprises: applying a clustering algorithm to group the plurality of facial images into a plurality of clusters; andselecting a cluster of the plurality of cluster that has a highest cluster purity;wherein the selected subset of facial images comprises the facial images in the selected cluster; andestimating one or more demographic characteristics of the user based on the selected subset of facial images.
地址 Tokyo JP