PROJECT TITLE :
Multifocus Image Fusion Based on NSCT and Focused Area Detection
To beat the difficulties of sub-band coefficients choice in multiscale transform domain-based mostly image fusion and solve the problem of block effects suffered by spatial domain-primarily based image fusion, this paper presents a novel hybrid multifocus image fusion method. Initial, the supply multifocus images are decomposed using the nonsubsampled contourlet remodel (NSCT). The low-frequency sub-band coefficients are fused by the sum-modified-Laplacian-based mostly local visual distinction, whereas the high-frequency sub-band coefficients are fused by the native Log-Gabor energy. The initial fused image is subsequently reconstructed primarily based on the inverse NSCT with the fused coefficients. Second, after analyzing the similarity between the previous fused image and the supply images, the initial focus area detection map is obtained, which is employed for achieving the choice map obtained by employing a mathematical morphology postprocessing technique. Finally, primarily based on the decision map, the final fused image is obtained by choosing the pixels in the focus areas and retaining the pixels in the main focus region boundary as their corresponding pixels in the initial fused image. Experimental results demonstrate that the proposed technique is better than numerous existing rework-based fusion strategies, together with gradient pyramid rework, discrete wavelet transform, NSCT, and a spatial-based mostly method, in terms of each subjective and objective evaluations.
Did you like this research project?
To get this research project Guidelines, Training and Code... Click Here