MRI Images based Brain Tumour Detection System

Abstract

Brain tumor detection is a challenging task and it’s very important to analyze the structure of the tumor correctly so an automatic method is used now a day for the detection of the tumor. This method saves time as well as it reduces the error which occurs in the method of manual detection. This proposed method is a new technique which not only detect tumor but also calculate percentage area occupied by tumor cells compared with total brain cells. Circular Hough transform is used for encircling the affected area and to estimate relative affected area. KNN& LLOYED are used for detecting and differentiating tumor affected tissues with not affected tissues. Perform wavelet transform on the converted Gray scale image and extracted 12 features like contrast, correlation, energy, homogeneity etc. DB5 wavelet transform is used for feature extraction