基于图像的皮肤纹理评价算法研究

doi:10.13218/j.cnki.csdc.2018.12.006

日用化学工业 ›› 2018, Vol. 48 ›› Issue (12): 695-701.doi: 10.13218/j.cnki.csdc.2018.12.006

基于图像的皮肤纹理评价算法研究

陈文睿^1,2, 陈天华^1,2, 王小艺^1,2, 许继平^1,2, 于家斌^1,2, 王英强³

1.北京工商大学中国轻工业化妆品重点实验室,北京 100048;
2.北京工商大学计算机与信息工程学院,北京 100048;
3.北京四海耕耘科技有限公司,北京 100036

收稿日期:2018-04-01 出版日期:2018-12-22 发布日期:2019-03-18
通讯作者: 陈天华,教授,电话：13621123681,邮箱：cth188@sina.com。
作者简介:陈文睿(1995-),女,北京人,硕士研究生,电话：13321157380,邮箱：chenwr01@sina.com。
基金资助:
北京工商大学中国轻工业化妆品重点实验室开放课题基金资助项目(KLC-2017-ZD1)

Research on image-based skin texture evaluation algorithm

CHEN Wen-rui^1,2, CHEN Tian-hua^1,2, WANG Xiao-yi^1,2, XU Ji-ping^1,2, YU Jia-bin^1,2, WANG Ying-qiang³

1.China Key Laboratory of Light Industry Cosmetics,Beijing Technology and Business University,Beijing 100048,China;
2.School of Computer and Information Engineering,Beijing Technology and Business University,Beijing 100048,China;
3.Beijing Sihaigengyun Technology Co.,Ltd.,Beijing 100036,China

Received:2018-04-01 Online:2018-12-22 Published:2019-03-18

摘要/Abstract

摘要： 皮肤表面纹理或微轮廓的量化评价对抗皱宣称的化妆品功效评价有重要意义。基于皮肤美容领域的应用需求和日常生活的实际需要,结合图像处理领域的相关算法,对皮肤的基础纹理特征展开了研究。首先,将实验实测的皮肤图像转为灰度图像,再通过对比度受限的自适应直方图均衡化对图像进行增强,之后通过高斯滤波去除图像的噪声,再采用维纳滤波对纹理的细节信息进行增强,得到纹理清晰的皮肤图像。通过实验确定适合于皮肤纹理评价的灰度共生矩阵的灰度级数和距离,基于灰度共生矩阵算法对皮肤纹理进行统计分析,提出了基于4个纹理特征参数的综合指标数学模型,并应用该模型对全部皮肤图像进行了纹理特征定量评价,同时也由专家对这些皮肤图像进行视觉盲评,2种评价方法一致性良好。

关键词: 化妆品功效评价, 皮肤纹理, 图像预处理, 灰度共生矩阵算法, 综合指标

Abstract: Quantitative evaluation of skin texture or micro-contour is of great significance for evaluating the efficacy of cosmetics against wrinkles.Skin texture,as one of the inherent characteristics of the skin,has a significant effect on skin quality.Based on the application requirements of skin beauty and the actual needs of daily life,the basic texture features of the skin were studied by the related algorithms in the field of image processing.Firstly,the experimentally measured skin image was transformed into a grayscale image.The image was then enhanced by contrast limited adaptive histogram equalization.Then the noise of the image was removed by Gauss filtering,and the details of the texture were enhanced by Wiener filtering.A clear texture of the skin image was obtained.The gray scale and distance of gray level co-occurrence matrix suitable for skin texture evaluation were determined through experiments.The skin texture was statistically analyzed based on gray level co-occurrence matrix algorithm.A mathematical model of comprehensive index based on four texture feature parameters was proposed,and the texture features of all skin images were quantitatively evaluated by using the model.Visual evaluation of these skin images was also conducted by experts.The two methods of evaluation are in good agreement.

Key words: cosmetic efficacy evaluation, skin texture, image preprocessing, gray level co-occurrence matrix algorithm, synthesis index

中图分类号:

TQ658

陈文睿, 陈天华, 王小艺, 许继平, 于家斌, 王英强. 基于图像的皮肤纹理评价算法研究[J]. 日用化学工业, 2018, 48(12): 695-701.

CHEN Wen-rui, CHEN Tian-hua, WANG Xiao-yi, XU Ji-ping, YU Jia-bin, WANG Ying-qiang. Research on image-based skin texture evaluation algorithm[J]. China Surfactant Detergent & Cosmetics, 2018, 48(12): 695-701.

参考文献

[1] Li Chengtong,Zhao Hua,Wang Min.Efficacy evaluation of cosmetics (IX):Application of image analysis in cosmetic efficacy evaluation[J].China Surfactant Detergent & Cosmetics,2018,48(10):551-557.
[2] Yin Yuexuan,Zhao Hua.Efficacy evaluation of cosmetics (I):Scientific support for cosmetics efficacy claims[J].China Surfactant Detergent & Cosmetics,2018,48(1):8-13.
[3] Li Lingyu.Design of skin aging evaluation system based on machine vision [D].Chongqing:Chongqing Medical University,2016.
[4] Yu Shengwei.Analysis and application of noise filtering in MATLAB image filtering [M].Beijing:Beijing University of Aeronautics and Astronautics Press,2015.
[5] Yan Weizhong,Xu Yinli,Qiao Xi,et al.Underwater sea cucumber image enhancement method based on contrast limited histogram equalization[J].Journal of Agricultural Engineering,2016,32(6):197-203.
[6] Cai Chaofeng,Ren Jingying.Contrast enhancement of hand vein image based on histogram equalization[J].Computer Application,2013,33(4):1125-1127.
[7] Huber M.Gaussian filter based on deterministic sampling for high quality nonlinear estimation[J].IFAC Proceedings Volumes,2008,41(2):13527-13532.
[8] Song Jiali.Extraction and analysis of skin texture image features [D].Liaoning:Northeastern University,2009.
[9] Wang Yuanmei,Tao Li.Application of wavelet and wiener filtering algorithm in image de-noising[J].Open Access Library Journal,2016,3(1):1-7.
[10] Madzarov G,Gjorgjevikj D.Multi-class classification using support vector machines in decision tree architecture[C]// IEEE EUROCON 2009.Saint Petersburg:Electrotechnical University,2009:288-295.
[11] Li Lingyu,Xue Jinxia,He Xiangqian,et al.Research on skin aging grading based on machine vision[J].Journal of Biomedical Engineering,2017(3):449-455.
[12] Jiao Pengpeng,Guo Yizheng,Liu Lijuan,et al.Matlab implementation of texture feature extraction from gray level co-occurrence matrix[J].Computer Technology and Development,2012(11):169-171.
[13] Li Tianqi.Research on surface roughness detection technology [D].Heilongjiang:Northeast Forestry University,2016.
[14] Xue Jinxia,Li Lingyu,Gan Ping,et al.Research on inferring age based on skin surface texture information[J].Journal of Chongqing Medical University,2017(2):205-208.
[15] Zulfikar Z,Zulhelmi Z.Statistical investigation of skin image for disease analyzing in rural area using Matlab[C]//2017 6^th International Conference on Electrical Engineering and Informatics.Langkawi:Faculty of Information Science & Technology,2017:189-194.
[16] Chen Tianhua,Wang Xiaoyi,Xu Jiping,et al.Quantitative co-occurrence matrix based method for skin condition evaluation:CN106600585A[P].2017-07-14.

基于图像的皮肤纹理评价算法研究

Research on image-based skin texture evaluation algorithm

PDF (PC)

赞

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 5

Metrics

本文评价

推荐阅读 10

[1]	马月滢, 刘琦, 加萌, 王俊杰, 王玮, 赵华. 一款紧致化妆品的功效评价方法研究[J]. 日用化学工业（中英文）, 2024, 54(1): 73-79.
[2]	谭淇丹, 毕永贤, 刘蕾, 胡雪情, 代晓艳. 化妆品舒缓功效评价的研究现状[J]. 日用化学工业（中英文）, 2023, 53(2): 193-201.
[3]	曹晨灿, 谭淇丹, 刘蕾, 杨小玉, 陈海峰. 用于抗糖化功效评价的细胞模型研究现状及应用前景[J]. 日用化学工业（中英文）, 2023, 53(12): 1451-1458.
[4]	李潇, 张晓娥, 卢永波, 金岩. 化妆品功效评价(Ⅷ)—— 3D皮肤模型在化妆品功效评价中的应用[J]. 日用化学工业, 2018, 48(9): 489-494.
[5]	郭立群,王敏. 化妆品功效评价(Ⅶ)——细胞生物学在化妆品功效评价中的应用[J]. 日用化学工业, 2018, 48(7): 371-377.