北京生物医学工程

基于直方图均衡化的伽马校正和K-means聚类的舌象苔质分离方法

Separation method of tongue coating and body of tongue image based on histogram equalization and gamma correction and K-means clustering

作者：韩立博胡广芹张新峰冯利李泉旺蔡轶珩

单位：北京工业大学信息学部（北京 100124）<p>中国医学科学院肿瘤医院（北京 100021）</p><p>北京中医药大学东方医院（北京 100078）</p>

关键词：肿瘤；舌苔舌质分离；直方图均衡化；伽马校正； K-means聚类； a*通道

分类号：R318.04

出版年·卷·期（页码）：2019·38·1（1-6）

摘要：

目的舌苔舌质分离对后续肿瘤患者舌象的客观化辨证具有重要的意义。常用的算法是基于颜色空间通道舌图像的k-means聚类算法。CIEL*a*b*颜色空间的a*通道舌图像相较于其他颜色空间通道的舌图像分割结果稳定，常用来后续的分割。但对于部分舌图像而言，a*通道舌图像的舌苔、舌质虽然具有一定的区分度，但二者的区分度并不是十分明显，影响后续的分割结果。因此，本文提出一种基于直方图均衡化的伽马校正和K-means聚类的舌苔舌质分离方法。方法采用200幅肿瘤患者的舌图像作为实验样本。首先将舌图像从RGB颜色空间转换到CIEL*a*b*颜色空间，对a*通道舌图像进行直方图均衡化增强以及伽马校正，然后利用k-means聚类方法对增强后的舌图像舌苔舌质分离。得到直方图均衡化以及伽马校正后的a*通道舌图像和分割后的舌苔、舌质图像。为了验证算法的可行性，请5位专业中医医生对200例肿瘤患者的舌图像舌苔、舌质分割效果进行辨析。结果进行直方图均衡化以及伽马校正后的a*通道舌图像舌苔、舌质分割结果明显强于未经处理的a*通道舌图像分割结果。经辨析，分割合格率为97%。结论该方法可以很好地实现舌苔舌质分离，具有一定的应用价值。

Objective Tongue coating and body separation has an important significance to the subsequent objective syndrome differentiation of tongue images of tumor patients. The common algorithms are K-means clustering algorithm based on tongue image of color space channels.The a* channel tongue image in CIEL*a*b* color space is stable compared with other color space channels in tongue segmentation.It is often used for subsequent segmentation.For some tongue images, tongue coating and body of the a* channel have a certain degree of differentiation , but the degree of discrimination between the two is not very obvious,which affects the subsequent segmentation results. Therefore, we designed a separation method of tongue coating and body based on histogram equalization and gamma correction and K-means clustering. Methods 200 tongue images of tumour patients were used as experimental samples. Firstly, the tongue image was transformed from RGB color space to CIEL*a*b* color space.The tongue image of the a* channel was enhanced by histogram equalization and gamma correction. Secondly, tongue coating and body of enhanced tongue image was separated by the K-means clustering method. The histogram equalization and the gamma corrected a* channel tongue image and the segmented tongue coating and tongue body images were obtained.In order to verify the feasibility of the algorithm, five professional Chinese medicine doctors were asked to discriminate results of tongue coating and tongue body segmentation on 200 patients with tumors. Results The tongue coating and body segmentation results of the a* channel tongue image after histogram equalization and gamma correction are obviously better than unprocessed a* channel tongue image segmentation results.After analysis, the qualified rate of segmentation is 97%.Conclusions This method can achieve good separation of tongue coating and body and has a certain application value.

参考文献：

[1]吴万垠.中医肿瘤诊疗中的诊断、辨病、辨证与辨症[J].中国中西医结合杂志,2018,38(2):156-158.

[2]高清河,刚晶,王和禹,刘海英.舌诊图像分割和特征提取的方法研究与应用[J].中国中医药现代远程教育,2017,15(13):147-149.

Gao QH, Gang J, Wang HY, et al. Research and application of tongue image segmentation and feature extraction method in traditional Chinese medicine[J]. Chinese Medicine Modern Distance Education of China, ,2017,15(13):147-149.

[3]Kawanabe T, Kamarudin N D, Ooi C Y, et al. Quantification of tongue colour using machine learning in Kampo medicine[J]. European Journal of Integrative Medicine, 2016,8(6):932-941.

[4]杜建强,卢炎生.一种中医舌象的舌质舌苔分离方法[J].计算机应用研究,2009,26(07):2762-2764.

Du JQ, Lu YS. Separation algorithm of tongue body and tongue coating[J]. Application Research of Computers, 2009, 26 (7):2762-2764.

[5]Wei CC, Wang CH, Huang S W. Using threshold method to separate the edge, coating and body of tongue in automatic tongue diagnosis[C]. The 6th International Conference on Networked Computing and Advanced Information Management, Seoul, 2010, pp. 653-656.

[6]方衡.基于改进的最大类间方差的舌色和舌苔分离技术[J].电脑知识与技术,2008,3(4):711-713.

Fang H. Based on advenced otsu methord separating the tongue coating and the tongue image[J]. Computer Knowledge & Technology, 2008，3(4):711-713

[7]许家佗,屠立平,张志枫,等.基于图像区域分割方法的舌质与舌苔识别[J].上海中医药大学学报,2009,23(03):42-45.

Xu JT, Tu LP, Zhang ZF,et al. Identification of tongue body and fur based on color image region separation[J]. Acta Universitatis Traditionis Medicalis Sinensis Pharmacologiaeque Shanghai, 2009,23(03):42-45.

[8]Kamarudin N D, Ooi C Y, Kawanabe T, et al. A fast and effective segmentation algorithm with automatic removal of ineffective features on tongue images[J]. Jurnal Teknologi ,2016, 78(8):153-163.

[9]李兆龙,苏育挺.一种基于聚类的舌苔舌质分离方法[J].南开大学学报(自然科学版),2017,50(04):52-56+62.

Li ZL, Su YT. A kind of method for separation between tongue coating and nature based on clustering[J]. Acta Scientiarum Naturalium Universitatis Nankaiensis,2017,50(04):52-56+62.

[10]郭宙,杨学智,司银楚,等.基于K-均值聚类的常用色彩空间舌质舌苔分割研究[J].北京中医药大学学报,2009,32(12):819-821+871.

Guo Z, Yang XZ, Si YC, et al. Segmentation of tongue body and fur based on common color spaces of Kmeans clustering[J]. Journal of Beijing University of Traditional Chinese Medicine, 2009,32(12):819-821+871.

[11]王学民,吕元婷,王瑞云,等.基于双光源的舌质舌苔分离方法研究[J].纳米技术与精密工程,2016,14(06):434-439.

Wang XM, Lv YT , Wang RY, et al. Research on separation method of tongue body and coating based on double light sources[J]. Nanotechnology & Precision Engineering, 2016,14(06):434-439.

[12]杨飚,杨芩.Lab颜色空间和形态学处理相结合的双行车牌定位方法[J].科学技术与工程,2014,14(26):108-110+130.

Yang B, Yang Q. Two-line license plate detection method based on CIELab space and morphological processing[J]. Science Technology & Engineering, 2014,14(26):108-110+130.

[13]陈守刚.基于直方图均衡化的彩色图像增强研究[J].重庆三峡学院学报,2011,27(03):74-77.

Chen SG. Color image enhancement based on histogram equalization[J]. Journal of Chongqing Three Gorges University,2011,27(03):74-77.

[14]张铮 ,徐超，任淑霞，等.数字图像处理与机器视觉:Visual C++与Matlab实现[M].北京：人民邮电出版社，2015.8.

[15]崔艳军,张文峰,李建欣，等.条纹投影三维测量的Gamma畸变校正方法[J].光学学报,2015,35(1):161-170.

Cui YJ, Zhang WF, Li JX, et al. A method of gamma correction in fringe projection measurement[J]. Acta Optica Sinica,2015,35(1):161-170.

[16] Shi CZ, Wang YN, Xiao BH, et al. OTSU guided adaptive binarization of CAPTCHA image using gamma correction[C]. 2016 23rd International Conference on Pattern Recognition (ICPR), Cancun, 2016, pp. 3962-3967.

[17]周飞,贾振红,杨杰，等.基于剪切波域改进Gamma校正的医学图像增强算法[J].光电子·激光,2017,28(05):566-572.

Zhou F, Jia H, Yang J, et al. Medical image enhancement method based on improved Gamma correction in Shearlet domain[J]. Guangdianzi Jiguang/journal of Optoelectronics Laser, 2017, 28(05):566-572.

[18]吴迪,刘伟峰,胡胜,等.基于Lab空间的K均值聚类彩色图像分割[J].电子科技,2017,30(10):29-32.

Wu D , Liu WF,Hu S, et al. Color image segmentation using k-mean clustering based on lab space[J]. Electronic Science & Technology, 2017,30(10):29-32.

[19]Kumar B, Maheshkar SV, Bist AS. Image segmentation using enhanced K-means clustering with divide and conquer approach[J]. International Journal of Engineering Sciences & Research Technology, 2014, 3(7):188-196

服务与反馈：

【文章下载】【加入收藏】

提示：您还未登录，请登录！点此登录