Image fusion for face recognition

Despite the variety of approaches and tools studied, face recognition is not accurate or robust enough to be used in uncontrolled environments. Recently, infrared (IR) imagery of human face is considered as a promising alternative to visible imagery due to its relative insensitive to illumination changes. However, IR has its own limitations. In order to fuse information from the two modalities to achieve better result, we propose a new fusion recognition scheme by using non-separable wavelet frame transform (NWFT) and independent component analysis (ICA). Recognition rate is used to evaluate the proposed scheme. Experimental results show the scheme improves recognition performance substantially.