Occluded Face Recognition Using Low-rank Regression with Generalized Gradient Direction
This addresses the challenge of face recognition in occluded scenarios, which is important for security and surveillance applications, but it appears to be an incremental improvement over prior methods.
The paper tackles the problem of recognizing faces with occlusions by proposing a method that uses gradient direction features and a hierarchical sparse and low-rank regression model, achieving state-of-the-art performance compared to existing methods, including CNN-based approaches, on real-world and synthesized occlusion data.
In this paper, a very effective method to solve the contiguous face occlusion recognition problem is proposed. It utilizes the robust image gradient direction features together with a variety of mapping functions and adopts a hierarchical sparse and low-rank regression model. This model unites the sparse representation in dictionary learning and the low-rank representation on the error term that is usually messy in the gradient domain. We call it the "weak low-rankness" optimization problem, which can be efficiently solved by the framework of Alternating Direction Method of Multipliers (ADMM). The optimum of the error term has a similar weak low-rank structure as the reference error map and the recognition performance can be enhanced by leaps and bounds using weak low-rankness optimization. Extensive experiments are conducted on real-world disguise / occlusion data and synthesized contiguous occlusion data. These experiments show that the proposed gradient direction-based hierarchical adaptive sparse and low-rank (GD-HASLR) algorithm has the best performance compared to state-of-the-art methods, including popular convolutional neural network-based methods.