Mean shift segmentation on Enhanced Color image

Abstract

This paper proposed the method of mean shift segmentation on Enhanced color image. The method applies the modified histogram equalization technique for enhancement of under illuminated color image and then mean shift segmentation is applied on this enhanced image. This technique uses the lightness component in YIQ color space is transformed using sigmoid function, then the traditional histogram equalization (HE) method is applied on Y component. Once the image is enhanced mean shift segmentation is applied to the enhanced image due to which we get good segmentation results as compared to without enhanced image. Experiments on natural color images show promising results.