Continuous Pose Normalization for Pose-Robust Face Recognition
- 27 August 2012
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Signal Processing Letters
- Vol. 19 (11), 721-724
- https://doi.org/10.1109/lsp.2012.2215586
Abstract
Pose variation is a great challenge for robust face recognition. In this paper, we present a fully automatic pose normalization algorithm that can handle continuous pose variations and achieve high face recognition accuracy. First, an automatic method is proposed to find pose-dependent correspondences between 2-D facial feature points and 3-D face model. This method is based on a multi-view random forest embedded active shape model. Then we densely map each pixel in the face image onto the 3-D face model and rotate it to the frontal view. The filling of occluded face regions is guided by facial symmetry. Recognition experiments were conducted on the two western databases CMU-PIE, FERET and one eastern database CAS-PEAL. Currently the algorithm has been trained with pose variation up to ±50° in yaw. Our algorithm not only achieves high recognition accuracy for learnt poses but also shows good generalizability for extreme poses. Furthermore, it suggests the promising application to people of different races.Keywords
This publication has 18 references indexed in Scilit:
- 3D face sparse reconstruction based on local linear fittingThe Visual Computer, 2013
- Head Pose Estimation Based on Random Forests for Multiclass ClassificationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2010
- 2D face fitting-assisted 3D face reconstruction for pose-robust face recognitionSoft Computing, 2009
- A 3D Face Model for Pose and Illumination Invariant Face RecognitionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2009
- Toward Pose-Invariant 2-D Face Recognition Through Point Distribution Models and Facial SymmetryIEEE Transactions on Information Forensics and Security, 2007
- Locally Linear Regression for Pose-Invariant Face RecognitionIEEE Transactions on Image Processing, 2007
- Real-time multi-view face detection and pose estimation based on cost-sensitive AdaBoostTsinghua Science and Technology, 2005
- The CMU pose, illumination, and expression databaseIeee Transactions On Pattern Analysis and Machine Intelligence, 2003
- Gabor feature based classification using the enhanced fisher linear discriminant model for face recognitionIEEE Transactions on Image Processing, 2002
- View-based active appearance modelsImage and Vision Computing, 2002