研究皮肤纹理经过UVB光照射后的变化情况并对其进行识别。具体地, 采取图像纹理分析方法, 对经过光照射后不同时期的小鼠皮肤图像提取纹理特征, 进而建立一种新的皮肤纹理识别模型。采用空间灰度共生矩阵法提取图像纹理的4个主要特征, 即: 能量, 熵, 惯性矩, 相关度, 然后利用神经网络中的NNtool对皮肤纹理图像进行训练和分类识别。实验结果很好地证明了这种纹理分析和识别方法的可行性和有效性。

Studying the change and identification of skin texture after UVB light.Concretely, the texture characteristic of mice skin irradiated by the UVB light in different periods was extracted by spatial gray level co-occurrence matrix. Then, a new kind of skin texture recognition model was established. Training and recognizing the four main texture characters, including angular second moment, entropy, contrast, and correlation of skin in various statues were completed by using NNtool of neural network. The results indicated that this kind of texture analysis and identification is a feasible and effective method.