Face Clustering in Photo Album

Digital photo management is becoming indispensable for the explosively growing family photo albums due to the rapid popularization of digital cameras and mobile phone cameras. An effective photo management system could accurately and efficiently group all faces of the same person into a small number of clusters. In this paper, we present a novel photo grouping method based on spectral theory. The key idea is to utilize prior information of family photo albums to improve the performance. First, an individual can only appear once in one photo, which works as the similarity constraint in our graph construction. Second, an individual cannot show more times than the number of photos in each album. That is, the size of a cluster for an individual is at most the number of photos in an album. We consider this constraint as a Minimum Cost Flow (MCF) linear network optimization problem and therefore propose a constrained K-Means for data clustering after graph embedding. Two metrics, i.e., accuracy (AC) and normalized mutual information metric (NMI), are used to evaluate the clustering performance. Extensive experimental results demonstrate the effectiveness of the proposed method.