Sparse graphical representation based discriminant analysis for heterogeneous face recognition

摘要

Face images captured in heterogeneous environments, e.g., sketches generated by the artists or composite generation software, photos taken by common cameras and infrared images captured by corresponding infrared imaging devices, are usually subject to large texture (i.e., style) differences. This results in heavily degraded performance of conventional face recognition methods directly applied on heterogeneous face images. In this paper, we propose a novel sparse graphical representation based discriminant analysis (SGR-DA) approach to address aforementioned cross-modality face recognition scenarios. An adaptive sparse graphical representation scheme is designed to represent face images from different modalities, where a Markov networks model is constructed to generate adaptive sparse vectors. To handle the complex facial structure and further improve the discriminability, a spatial partition-based discriminant analysis framework is presented to refine the adaptive sparse vectors for face matching. We conducted experiments on six commonly used heterogeneous face datasets and experimental comparison with both traditional and deep learning based approaches illustrated the superiority of our proposed SGR-DA. (C) 2018 Elsevier B.V. All rights reserved.