Expectation-Maximization with Distance Measure for Color Image Segmentation

Abstract

In this paper we propose an expectation-maximization (EM) algorithm with distance measure for color image segmentation. The probability distribution model used is the Gaussian mixture model. The concept of color distance measure is used in this algorithm to determine the region to which a particular pixel belongs. L *a* b color space is used to replace the more straightforward spaces such as the RGB color space and YUV color space. This algorithm is capable of automatically selecting the number of components of the model using minimum description length (MDL) criterion. The proposed method yields good segmentation with better PSNR and SSIM values compared to classical EM algorithm; that is, the segmented image will be structurally more similar to the original image.