Random Faces Guided Sparse Many-to-One Encoder for Pose-Invariant Face Recognition
Yizhe Zhang, Ming Shao, Edward K. Wong, Yun Fu; Proceedings of the IEEE International Conference on Computer Vision (ICCV), 2013, pp. 2416-2423
Abstract
One of the most challenging task in face recognition is to identify people with varied poses. Namely, the test faces have significantly different poses compared with the registered faces. In this paper, we propose a high-level feature learning scheme to extract pose-invariant identity feature for face recognition. First, we build a single-hiddenlayer neural network with sparse constraint, to extract poseinvariant feature in a supervised fashion. Second, we further enhance the discriminative capability of the proposed feature by using multiple random faces as the target values for multiple encoders. By enforcing the target values to be unique for input faces over different poses, the learned highlevel feature that is represented by the neurons in the hidden layer is pose free and only relevant to the identity information. Finally, we conduct face identification on CMU MultiPIE, and verification on Labeled Faces in the Wild (LFW) databases, where identification rank-1 accuracy and face verification accuracy with ROC curve are reported. These experiments demonstrate that our model is superior to other state-of-the-art approaches on handling pose variations.
Related Material
[pdf]
[
bibtex]
@InProceedings{Zhang_2013_ICCV,
author = {Zhang, Yizhe and Shao, Ming and Wong, Edward K. and Fu, Yun},
title = {Random Faces Guided Sparse Many-to-One Encoder for Pose-Invariant Face Recognition},
booktitle = {Proceedings of the IEEE International Conference on Computer Vision (ICCV)},
month = {December},
year = {2013}
}