Structured Occlusion Coding for Robust Face Recognition

TL;DR

This paper introduces Structured Occlusion Coding (SOC), a novel approach for robust face recognition under occlusion, utilizing structured dictionaries and sparsity to improve accuracy in practical scenarios with predictable occlusions.

Contribution

The paper proposes a new structured occlusion coding method that employs structured dictionaries and sparsity, along with an occlusion mask estimation technique, to enhance face recognition robustness.

Findings

SOC outperforms existing methods on public datasets.

Structured sparsity improves robustness against large occlusions.

The occlusion mask estimation via LCD significantly enhances occlusion handling.

Abstract

Occlusion in face recognition is a common yet challenging problem. While sparse representation based classification (SRC) has been shown promising performance in laboratory conditions (i.e. noiseless or random pixel corrupted), it performs much worse in practical scenarios. In this paper, we consider the practical face recognition problem, where the occlusions are predictable and available for sampling. We propose the structured occlusion coding (SOC) to address occlusion problems. The structured coding here lies in two folds. On one hand, we employ a structured dictionary for recognition. On the other hand, we propose to use the structured sparsity in this formulation. Specifically, SOC simultaneously separates the occlusion and classifies the image. In this way, the problem of recognizing an occluded image is turned into seeking a structured sparse solution on occlusion-appended dictionary. In order to construct a well-performing occlusion dictionary, we propose an occlusion mask estimating technique via locality constrained dictionary (LCD), showing striking improvement in occlusion sample. On a category-specific occlusion dictionary, we replace norm sparsity with the structured sparsity which is shown more robust, further enhancing the robustness of our approach. Moreover, SOC achieves significant improvement in handling large occlusion in real world. Extensive experiments are conducted on public data sets to validate the superiority of the proposed algorithm.