Detection and Demarcation of Tumor using Vector Quantization in MRI images

Segmenting a MRI images into homogeneous texture regions representing tissue types is often a useful preprocessing step in the-assisted detection of breast cancer. That is why we proposed new to detect cancer in mammogram breast cancer images. In this paper we segmentation using vector quantization technique. Here we used Linde-Gray algorithm (LBG) for segmentation of MRI images. Initially a codebook size 128 was generated for MRI images. These code vectors were further in 8 clusters using same LBG algorithm. These 8 images were displayed a result. This approach does not leads to over segmentation or under. For the comparison purpose we displayed results of watershed and Entropy using Gray Level Co-occurrence Matrix along with this.