基于灰度共生矩阵的人体皮肤纹理分析  

An Analysis on Human Skin Texture Based on Gray-level Co-occurrence Matrix

作　　者：许舒斐[1] 吴淑莲[1] 李晖[1] 

机构地区：[1]福建师范大学物理与光电信息科技学院医学光电科学与技术教育部重点实验室福建省光子技术重点实验室,福建福州350007

出　　处：《激光生物学报》2011年第3期324-328,共5页Acta Laser Biology Sinica

基　　金：教育部新世纪优秀人才支持计划项目(NCET-04-0615);福建省自然科学基金项目(2010J01323)

摘　　要：对纹理图像的分析及特征提取是近年来图像处理领域的研究热点,在现实中有广泛的应用价值。灰度共生矩阵已被理论证明是图像纹理分析的一个很好的方法。为了使灰度共生矩阵所提取的特征值能够更好地描述皮肤老化的灰度分布信息,以不同年龄层的女性的不同部位的皮肤纹理图像作为研究对象,对采集到的图像进行预处理,采用灰度共生矩阵法提取纹理的特征值,通过统计分析得出了特征值的变化规律。实验结果对皮肤老化研究及其纹理分析有参考意义。The feature extraction and analysis of texture image have become the hot issue in recent image processing areas. It has entensive application value in the practice. The Gray Level Co-occurrence Matrix has been proved to be a promising method for image texture analysis. To make the statistical measures derived from Gray Level Co-occurrence Matrix provides better information about the image＇ s grayscale distribution in aging skin. Women with different ages in different parts of the skin texture images were extracted as the object of study. First the sampled images are preproeessed, then features are extracted from the image preproeessed based on gray level co-occurrence matrix. At last the changing rule of the statistics along with different parameters was obtained by statistical analysis in the study. It has been proved to be valuable reference for skin aging study and texture analysis.

关 键 词：灰度共生矩阵 皮肤纹理图像 特征值 

分 类 号：TP317.4[自动化与计算机技术—计算机软件与理论]