Title :
Face detection, pose estimation, and landmark localization in the wild
Author :
Zhu, Xiangxin ; Ramanan, Deva
Author_Institution :
Dept. of Comput. Sci., Univ. of California, Irvine, CA, USA
Abstract :
We present a unified model for face detection, pose estimation, and landmark estimation in real-world, cluttered images. Our model is based on a mixtures of trees with a shared pool of parts; we model every facial landmark as a part and use global mixtures to capture topological changes due to viewpoint. We show that tree-structured models are surprisingly effective at capturing global elastic deformation, while being easy to optimize unlike dense graph structures. We present extensive results on standard face benchmarks, as well as a new “in the wild” annotated dataset, that suggests our system advances the state-of-the-art, sometimes considerably, for all three tasks. Though our model is modestly trained with hundreds of faces, it compares favorably to commercial systems trained with billions of examples (such as Google Picasa and face.com).
Keywords :
computer vision; face recognition; object detection; pose estimation; trees (mathematics); Google Picasa; computer vision; face detection; face.com; global elastic deformation; in-the-wild annotated dataset; landmark estimation; landmark localization; pose estimation; topological changes; tree-structured models; Computational modeling; Detectors; Estimation; Face; Face detection; Google; Shape;
Conference_Titel :
Computer Vision and Pattern Recognition (CVPR), 2012 IEEE Conference on
Conference_Location :
Providence, RI
Print_ISBN :
978-1-4673-1226-4
Electronic_ISBN :
1063-6919
DOI :
10.1109/CVPR.2012.6248014