Multimodal medical image fusion work bench using feature level transforms

Abstract

Multi-modal Medical image fusion has recently emerged as a comprehensive analysis approach, which usually uses several transformation techniques. Multi-modal medical image fusion is the process of merging multiple images from single or multiple imaging modalities to improve the imaging quality with preserving the specific features. Medical image fusion covers a broad number of hot topic areas, including image processing, computer vision, pattern recognition, machine learning and artificial intelligence. And medical image fusion has been widely used in clinical for physicians to comprehend the lesion by the fusion of different modalities medical images. In this thesis, we devise a workbench composed of several learning model named as firefly algorithm which is to eliminate the squared error and optimizes through weighted entropy for fusion. In second phase, hybridasion of the discrete wavelet transform and discrete curvetlet transform is fused together to produce the effective results. In third phase, we derived a new fusion model in terms of unsupervised classification model termed as principle component analysis incorporating the structure and sparse constraints in the multi-modality images. The correlation and covariance analysis using Eigen value and Eigen vector improves the image fusion with more flexibility and accuracy newline