Comparison of Pixel-level and feature level image fusion methods

In recent times multiple imaging sensors are employed in several applications such as surveillance, medical imaging and machine vision. In these multi-sensor systems there is a need for image fusion techniques to effectively combine the information from disparate imaging sensors into a single composite image which enables a good understanding of the scene. The prevailing fusion algorithms employ either the mean or choose-max fusion rule for selecting the best coefficients for fusion at each pixel location. The choose-max rule distorts constants background information whereas the mean rule blurs the edges. Hence, in this proposed paper, the fusion rule is replaced by a soft computing technique that makes intelligent decisions to improve the accuracy of the fusion process in both pixel and feature based image fusion. Non Sub-sampled Contourlet Transform (NSCT) is employed for multi-resolution decomposition as it is demonstrated to capture the intrinsic geometric structures in images effectively. Experiments demonstrate that the proposed pixel and feature level image fusion methods provides better visual quality with clear edge information and objective quality indexes than individual multiresolution-based methods such as discrete wavelet transform and NSCT.