Infrared and Visible Image Fusion for Concealed Weapon Detection using Transform and Spatial Domain Filters

Image fusion is mandatory to enhance the object recognition in images by concatenating many sources of planetoid, aerial and ground-based imaging systems with other related data set. Image fusion is the methodology of overlapping at least a couple of pictures so that their combination enhances the overall information content. In literature, there are many algorithms, whose objective is the fusion of images to improve the characteristics of the final image. This work primarily presents a contrast between thee cosine harmonic transform of wavelet transform, guided filter algorithm and discrete form of Wavelet transform. It can be stated with simple observation that the image fusion techniques based on guided refining or masking retrieve a good visual resultant image. Their performance is evaluated on Standard “Gun” dataset with the help of three most widely used performance evaluation metrics. The experimentation and work done on MATLAB, validates the superiority of DCHWT based fusion algorithm over others.