Texture Image Segmentation Based on Gaussian Mixture Models and Gray Level Co-occurrence Matrix

A novel texture image segmentation method based on Gaussian mixture models (GMM) and gray level co-occurrence matrix (GLCM) and was proposed. The feature space was formed by eight statics generated by gray level co-occurrence matrix (GLCM) including mean, variance, angular second moment(ASM), entropy, inverse difference moment(IDM), contrast, homogeneity(HOM), correlation(COR). The parameters of Gaussian mixture models were estimated by expectation maximization (EM) algorithm. The experiment results show that the proposed method can get better segmentation results than paper and effectively enhance the segmentation precision of texture image.