皮肤老化是人体衰老进程中最明显的标志，对其进行定性或定量评价具有重要意义，并可广泛应用于人体衰老程度研究以及抗衰老措施功效评价等领域。针对传统人为皮肤老化分级的主观性，本文探索用自组织映射（SOM）神经网络实现对皮肤老化程度的自动分级。首先，采用便携式数码显微镜获取人体前臂腹侧皮肤图像，经图像处理分析，提取皮肤纹理参数：皮沟平均宽度和交点个数，用于表征皮肤纹理老化的变化情况；其次，将纹理参数值输入 SOM 神经网络，用于网络训练学习及分级。结果显示，本文所设计的基于机器视觉下的皮肤老化评价方法，与人工方法相比较，分类一致率达 80.8%，可实现较为客观且快速的皮肤老化分级
References
[1]
1. Makrantonaki E, Bekou V, Zouboulis C C. Genetics and skin aging. Dermatoendocrinol, 2012, 4(3): 280-284.
[2]
2. Fisher G J, Kang S, Varani J, et al. Mechanisms of photoaging and chronological skin aging. Arch Dermatol, 2002, 138(11): 1462-1470.
[3]
3. Rittié L, Fisher G J. Natural and sun-induced aging of human skin. Cold Spring Harb Perspect Med, 2015, 5(1): a015370.
6. Setaro M, Sparavigna A. Irregularity skin index (ISI): a tool to evaluate skin surface texture. Skin Res Technol, 2001, 7(3): 159-163.
[7]
7. Hashimoto K. New methods for surface ultrastructure: Comparative studies of scanning electron microscopy, transmission electron microscopy and replica method. Int J Dermatol, 1975, 13(6): 357-381.
[8]
8. Seddon J M, Egan K M, Zhang Y, et al. Evaluation of skin microtopography as a measure of ultraviolet exposure. Invest Ophthalmol Vis Sci, 1992, 33(6): 1903-1908.
10. Trojahn C, Dobos G, Schario M, et al. Relation between skin micro-topography, roughness, and skin age. Skin Res Technol, 2015, 21(1): 69-75.
[11]
11. Zou Yaobin, Song Enmin, Jin Renchao. Age-dependent changes in skin surface assessed by a novel two-dimensional image analysis. Skin Res Technol, 2009, 15(4): 399-406.
[12]
12. de Paepe K, Lagarde J M, Gall Y, et al. Microrelief of the skin using a light transmission method. Arch Dermatol Res, 2000, 292(10): 500-510.
20. Brighenti C, Sanz-Bobi M á. Auto-regressive processes explained by self-organized maps. Application to the detection of abnormal behavior in industrial processes. IEEE Trans Neural Netw, 2011, 22(12): 2078-2090.
