Image fusion via genetic search for face recognition

Face recognition has been an active research area in the recent years. Many different approaches have been studied but a completely successful solution has not been found yet. This thesis proposes an algorithm for fusing infrared and visible images for the purposes of face recognition. Our experiments have shown a significant improvement in the recognition performance of the fused images compared to the visible and infrared images alone. The major advantage of the proposed fusion method is that no assumptions need to be made for the image type and content. This is achieved by the use of genetic algorithms and fusion in the wavelet transform domain.