Twins Facial Similarity Impact on Conventional Face Recognition Systems

摘要

Variations in pose, expression, aging and disguise are considered as basic challenges in face recognition systems and several standard databases have been built to address these challenges. Twins face recognition, on the other hand, has not yet been studied because there is no database which includes face images of twins. In this paper we present a new unconstrained face database which contains 3,804 face images of 1,902 pairs of twins. These images were collected from different twins' festivals from the World Wide Web. We provided an analytical study to experiment the impacts of twins facial similarity on different face recognition algorithms. The results show that the algorithms are unable to meet an acceptable rate of identification performance on twins face database. In this paper descriptions of the database such as development process, organization as well as statistic information are also depicted in details.