作者: Tong Zhang , Hui Chao , Dan Tretter
DOI: 10.1007/978-3-642-17829-0_7
关键词:
摘要: In this paper, we present an approach to estimate dynamic relations among major characters in family photo collections. This is a fully automated procedure which first identifies collections through face clustering. Then, based on demographic estimation, facial similarity, coappearance information and people's positions photos, social of people such as husband/wife, parents/kids, siblings, relatives friends can be derived. A workflow proposed integrate the from different aspects order give optimal result. Especially, timestamps relation trees are displayed show evolution over time.