Fusion of multisensor images using Nonsubsampled Contourlet Transform and Fuzzy Logic

This paper presents a new fusion methodology for combining images obtained from multiple cameras using Non-Subsampled Contourlet Transform (NSCT) and Fuzzy Logic. Recent studies confirm nonsubsampled contourlet transform as an efficient tool for image fusion, as it can effectively capture inherent geometric structures in images. The proposed technique uses Non-Subsampled Contourlet Transform for multiresolution decomposition of the input images and fuzzy logic for computing the optimal fusion weights of the low-pass NSCT coefficients. The NSCT low-pass coefficients are weighted based on the activity level measurements made, in order to generate fused images of superior quality. The high frequency directional coefficients are fused, based on the local energy feature. Both pixel and region based fusion are performed using fuzzy logic and applied to multisensor images of different types. Experimental results obtained reveal that the fuzzy based fusion algorithms proposed achieve better performance when compared to the state-of-the-art fusion schemes such as dual tree complex wavelet transform (DT-CWT), NSCT and hybrid NSCT in terms of the various fusion quality evaluation metrics.