Effective Unconstrained Face Recognition by Combining Multiple Descriptors and Learned Background Statistics
Issue No. 10 - October (2011 vol. 33)
Lior Wolf , Tel-Aviv University, Tel-Aviv
Tal Hassner , The Open University of Israel, Raanana
Yaniv Taigman , Tel-Aviv University, Tel-Aviv
Computer vision systems have demonstrated considerable improvement in recognizing and verifying faces in digital images. Still, recognizing faces appearing in unconstrained, natural conditions remains a challenging task. In this paper, we present a face-image, pair-matching approach primarily developed and tested on the “Labeled Faces in the Wild” (LFW) benchmark that reflects the challenges of face recognition from unconstrained images. The approach we propose makes the following contributions. 1) We present a family of novel face-image descriptors designed to capture statistics of local patch similarities. 2) We demonstrate how unlabeled background samples may be used to better evaluate image similarities. To this end, we describe a number of novel, effective similarity measures. 3) We show how labeled background samples, when available, may further improve classification performance, by employing a unique pair-matching pipeline. We present state-of-the-art results on the LFW pair-matching benchmarks. In addition, we show our system to be well suited for multilabel face classification (recognition) problem, on both the LFW images and on images from the laboratory controlled multi-PIE database.
Face and gesture recognition, similarity measures, face recognition, image descriptors.
Y. Taigman, T. Hassner and L. Wolf, "Effective Unconstrained Face Recognition by Combining Multiple Descriptors and Learned Background Statistics," in IEEE Transactions on Pattern Analysis & Machine Intelligence, vol. 33, no. , pp. 1978-1990, 2010.