Performance Analysis of Fusion Based Brain Image Classification Using Minimum Distanceclassifier

Image fusion is well used for medical brain image classification. Wavelet transform is the most commonly used image fusion method, which fuses the source images' information in wavelet domain according to some fusion rules. But because of the uncertainties of the source images' contributions to the fused image, how to design a good fusion rule to integrate as much information as possible into the fused image becomes the most important problem. This paper focused to classify the brain image into normal and abnormal image using minimum distance classifier algorithm. The proposed methodology consists of spatial domain filter, fusion, clipping circuit and minimum distance classifier algorithm. The difference features are extracted from fused image and compared with trained extracted feature set. The low power architecture for the proposed brain image classification method is presented in this paper. The proposed hardware architecture consumes power of 151mW in CMOS 90nm technology.