In the recent past, image fusion based on computer aided technological quantitative methods has established to take place of conventional systems in biomedical technology. Image fusion is the process of integrating multiple images of the same scene into a single fused image to reduce the uncertainty and minimize the redundancy while extracting all the useful information from the source images. In this paper, the image pre-processing is carried out to improve the quality of the image. The anisotropic diffusion filter is used to remove the noises such as salt and pepper noise, speckle noise and random noise. The non linear multi resolution wavelet analysis is used for enhancing the contrast and brightness of image to emphasize the fusion process. The quality of the pre-processed image is validated by calculating the objective quality parameters. The image fusion using Genetic and Artificial Bee Colony Optimization approaches are utilized to fuse images from different sensors. This, in turn, helps to enhance the visualization. The proposed work further explores comparison between Genetic-based image fusion and Artificial Bee Colony Optimization fusion technique along with quality evaluation indices for image fusion like entropy; root means square error, peak signal to noise ratio. Experimental results obtained from the fusion process prove that the use of the Artificial Bee Colony Optimization based image fusion approach shows better results. It improves performance and reduces brain tumor error detection more accurately.
Volume 11 | 02-Special Issue
Pages: 308-317