Patch-based Face Recognition using a Hierarchical Multi-label Matcher

TL;DR

This paper introduces a hierarchical multi-label patch-based face recognition method that improves accuracy by combining local patch classifiers and hierarchical relationships, demonstrating significant performance gains on benchmark datasets.

Contribution

It presents a novel hierarchical multi-label matcher with multiple global matching strategies for patch-based face recognition, enhancing accuracy over existing systems.

Findings

Improves Rank-1 accuracy by 3% on UHDB31 dataset.

Achieves 0.18% higher accuracy on IJB-A dataset.

Effective in various face recognition tasks.

Abstract

This paper proposes a hierarchical multi-label matcher for patch-based face recognition. In signature generation, a face image is iteratively divided into multi-level patches. Two different types of patch divisions and signatures are introduced for 2D facial image and texture-lifted image, respectively. The matcher training consists of three steps. First, local classifiers are built to learn the local matching of each patch. Second, the hierarchical relationships defined between local patches are used to learn the global matching of each patch. Three ways are introduced to learn the global matching: majority voting, l1-regularized weighting, and decision rule. Last, the global matchings of different levels are combined as the final matching. Experimental results on different face recognition tasks demonstrate the effectiveness of the proposed matcher at the cost of gallery generalization. Compared with the UR2D system, the proposed matcher improves the Rank-1 accuracy significantly by 3% and 0.18% on the UHDB31 dataset and IJB-A dataset, respectively.