Cross-pose Face Recognition by Canonical Correlation Analysis

TL;DR

This paper introduces a method using canonical correlation analysis to improve face recognition across different poses by maximizing correlations between images of the same person in different poses, thereby enhancing pose-invariance.

Contribution

The paper proposes a novel application of CCA to mitigate pose variation in face recognition by learning pose-specific transformations that maximize intra-subject correlations.

Findings

Significantly improves recognition performance across poses.

Enhancement with holistic+local features achieves state-of-the-art results.

Method effectively achieves pose-invariance in face recognition.

Abstract

The pose problem is one of the bottlenecks in automatic face recognition. We argue that one of the diffculties in this problem is the severe misalignment in face images or feature vectors with different poses. In this paper, we propose that this problem can be statistically solved or at least mitigated by maximizing the intra-subject across-pose correlations via canonical correlation analysis (CCA). In our method, based on the data set with coupled face images of the same identities and across two different poses, CCA learns simultaneously two linear transforms, each for one pose. In the transformed subspace, the intra-subject correlations between the different poses are maximized, which implies pose-invariance or pose-robustness is achieved. The experimental results show that our approach could considerably improve the recognition performance. And if further enhanced with holistic+local feature representation, the performance could be comparable to the state-of-the-art.