Robust Face Recognition by Constrained Part-based Alignment

TL;DR

This paper introduces a Constrained Part-based Alignment (CPA) algorithm that improves face recognition accuracy across pose and expression variations by aligning facial parts based on a trainable model and shape constraints.

Contribution

The paper proposes a novel trainable CPA model that learns facial part appearances and shape configurations, enabling robust face recognition across pose and expression changes.

Findings

CPA outperforms existing methods on benchmark datasets.

CPA effectively handles pose, expression, and illumination variations.

The algorithm can be integrated with various classifiers for improved recognition.

Abstract

Developing a reliable and practical face recognition system is a long-standing goal in computer vision research. Existing literature suggests that pixel-wise face alignment is the key to achieve high-accuracy face recognition. By assuming a human face as piece-wise planar surfaces, where each surface corresponds to a facial part, we develop in this paper a Constrained Part-based Alignment (CPA) algorithm for face recognition across pose and/or expression. Our proposed algorithm is based on a trainable CPA model, which learns appearance evidence of individual parts and a tree-structured shape configuration among different parts. Given a probe face, CPA simultaneously aligns all its parts by fitting them to the appearance evidence with consideration of the constraint from the tree-structured shape configuration. This objective is formulated as a norm minimization problem regularized by graph likelihoods. CPA can be easily integrated with many existing classifiers to perform part-based face recognition. Extensive experiments on benchmark face datasets show that CPA outperforms or is on par with existing methods for robust face recognition across pose, expression, and/or illumination changes.