DWT Based Image Fusion Technique for Infrared and Visible Images Using Particle Swarm Optimization

Abstract

Image fusion is a technique of combining multiple images of the same scene and generate a single output. The fused image gives more detail information about a particular scene which further used in many image processing applications. In this paper, we proposed the image fusion technique to fused infrared and visible images. The proposed technique is used discrete wavelet transform to decomposed source images from the spatial domain to the frequency domain. First, the source infrared image is divided into a visual saliency map. Second, visible and infrared images are decomposed into low and high frequencies coefficient. Third, particle swarm optimization fusion rule is applied on coefficients of the visible and infrared image. Lastly, the inverse discrete wavelet transform is applied to obtain the final image. The performance of the proposed algorithm is compared with maximum intensity, average intensity, discrete wavelet transform, and discrete stationary wavelet transform fusion techniques by using image quality metrics. The experimental results show our proposed method works better in terms of visually and objectively.