A Method of Segmentation for Hyper spectral & Medical Images Based on Color Image Segmentation

Abstract

The paper propose an original and simple segmentation strategy based on the EM approach for hyper spectral images . In a first step, to simplify the input color textured image into a color image without texture. The final segmentation is simply achieved by a spatially color segmentation using feature vector with the set of color values contained around the pixel to be classified. The spatial constraint allows taking into account the inherent spatial relationships of any image and its colours. This approach provides effective PSNR for the segmented image. These results omit the better performance athe segmented images are compared with Watershed & Region Growing Algorithm. This approach provides the effective segmentation for the Spectral Images & Medical Images. With proposed approach it can be fascinated that the data obtained from the segmentation can provide accurate information from the huge images