Development of Improved Classification and Segmentation Technique for Brain Tumor Detection

Abstract: The tumor can be detected by segmentation of brain Magnetic Resonance Image (MRI). In the case of suspected brain tumor, the exact location and size of tumor can be determined by radiologist. In this work tumor is detected by various stages like pre-processing, segmentation, feature extraction and classifier. The approach of otsu segmentation is applied for the segmentation. Tumor feature is extracted by Discrete Wavelet Transform (DWT) and Gray Level Co-occurrence Matrix (GLCM). Classification is done by using hidden markov model and performance parameters are measured.

Keywords: HMM, Otsu’s segmentation, GLCM