Content-based photo album management using faces' arrangement

摘要: Photo album management, an application of content-based image browsing/retrieval, has attracted much attention in recent years. Identities individuals appearing photos are the most important aspect photo browsing. However, face recognition generally does not work effectively such situations due to large variations pose, illumination and sometimes poor quality images. We present a system for browsing albums. The automatically detects stores information about locations faces photos. A similarity function based on arrangement is defined. Photos then clustered using proposed clustering algorithm. also represents event composite image. built from representative that event. Experiments indicate features effective representing semantic content appropriate