[Show abstract][Hide abstract] ABSTRACT: This paper presents the implementation of face recognition system using JDL framework. Fusion of visible and thermal images enhances the recognition rate and efficiency under varying illumination conditions. In this system, registration of visible and thermal images is performed using Fourier based method and fusion is performed using Empirical Mode Decomposition (EMD). The feature extraction and face recognition is implemented with Block Independent Component Analysis (BICA) using K-NN classifier. It is found that the proposed system out performs the existing face recognition system using single sensor.