We consider the problem of matching face against iris images using ocular information. In biometrics, face and iris images are typically acquired using sensors operating in visible (VIS) and near-infrared (NIR) spectra, respectively. This presents a challenging problem of matching images corresponding to different biometric modalities, imaging spectra, and spatial resolutions. We propose the usage of ocular traits that are common between face and iris images (viz., iris and ocular region) to perform matching.
Iris matching is performed using a commercial software, while ocular regions are matched using three different techniques: Local Binary Patterns (LBP), Normalized Gradient Correlation (NGC), and Joint Dictionary-based Sparse Representation (JDSR). Experimental results on a database containing 1358images of 704 subjects indicate that ocular region can provide better performance than iris biometric under a challenging cross-modality matching scenario.