Polarimetric thermal-to-visible heterogeneous face recognition using coupled independent component analysis

Abstract

Heterogeneous face recognition (HFR) refers to matching face imagery across different domains, such as identifying a thermal probe image given a gallery of visible face images. In this paper, we propose a method for thermal to visible face recognition based on coupled independent component analysis (Coupled ICA). It has been reported that independent component analysis (ICA) of natural scene patches produces a set of visual filters that resemble the receptive fields of simple cells in visual cortex and the projection matrix form a basis of images. Aiming to learn a common latent space for cross-modal images, we propose to learn a separate set of ICA filters which represent the respective imaging system in each domain using a coupled architecture. Coupled ICA assumes the image sources from one domain to be identical to those observed at the other domain. Pairs of image patches in the two domains jointly update the projection matrix in Coupled ICA model. The obtained ICA filters are used to transform images into a domain-independent latent space via patch-wise synthesis. In addition, we add cross-examples into a one-vs-all sparse representation (SR) classification strategy to improve classification performance. Experiments were conducted with the ARL Multi-modal Face Dataset. The results show that the proposed method can fuse the thermal and visible images and outperforms the state-of-the-art methods of cross-modal face recognition.