In this article a novel technique is introducing for performing the image fusion. As it is very familiar that more image information could be brought up by using image fusion process. Filter coefficients have been chosen in the DWT (Discrete Wavelet Transform) filter bank to perform DWT through optimization algorithm. The process of selecting filter coefficients through optimization process is known as ADWT (Adaptive Discrete Wavelet Transform). In this regard, satellite images with active sensor have been employed where these images are captured at same geo location but at different timings. Consequently, by satisfying the orthonormal properties filter coefficients have been chosen through Math-Flame Optimization (MFO) Algorithm. After performing the image fusion based on DWT by using optimized filter coefficients, the resultant image has been segmented with FCM-Clustering technique. Segmented image compared with the ground truth image. In this process input images are merged based on Particle Swarm Optimization (PSO) algorithm, Math-Flame Optimization (MFO) and Ant Lion Optimization Algorithm (ALO). Finally, the effectiveness of the proposed method is measured in terms of sensitivity, precision, selectivity, FDR and Accuracy.
Key words: ADWT, DWT, PSO, ALO, MFO, MSE and PSNR
|
