Fast and Accurate Brain Image Retrieval Using Gabor Wavelet Algorithm

Abstract— CBIR in medical image databases are used to assist physician in diagnosis the diseases and also used to aid diagnosis by identifying similar past cases. In order to retrieve a fast, accurate and an effective similarity of images from the large data set. The pre-processing step is extraction of brain. It removes the unwanted non-brain areas like scalp, skull, neck, eyes, ear etc from the MRI Head scan images. After removing the unwanted areas of non-brain region, it is very effective to retrieve the similar images. In this paper it is proposed a brain extraction technique using fuzzy morphological operators. For the experimental results 1200 MRI images are taken from scan centre and some brain images are collected from web and these have been implemented with popular brain extraction algorithm of GraphCut Algorithm (GCUT) and Expectation Maximization algorithm (EMA). The experiment result shows that the proposed algorithm fuzzy morphological operator algorithm (FMOA) is prompting the best promising results. Using this FMOA result retrieved the brain image from the large collection of databases using Gabor-Wavelet Transform. KeywordFuzzy morphological operator, T1-weighted MRI, Gabor-Wavelet Transform.