Skin Roughness Evaluation Method Based on gray level co-occurrence matrix

To evaluate the Skin roughness in the image of human, skin features arc based on eigenvalues of the gray level co-occurrence matrix are used, and the Pearson correlation coefficient is used to select the eigenvalues as the evaluation index. In the calculation of new eigenvalue, the normal equation is used to calculate the weight to improve the accuracy of the evaluation. In addition, a rough skin sample library is constructed manually to verify the experimental results of the evaluation method in this paper. In the experiments, the correct rate of the evaluation with the improved eigenvalues are presented by comparison with CON and IDM.