基于改进形态特征的牛乳体细胞分类识别算法
Milk Somatic Cells Recognition Based on Im-proved Morphological Features
DOI: 10.12677/CSA.2018.89147, PDF,    国家自然科学基金支持
作者: 章潇俪*, 薛河儒, 郜晓晶, 周艳青：内蒙古农业大学，计算机与信息工程学院，内蒙古 呼和浩特
关键词: 牛乳体细胞；形态特征；纹理特征；随机森林；Milk Somatic Cells； Morphological Feature； Texture Feature； Random Forest
摘要: 牛乳体细胞是牛乳质量评价和乳腺炎诊断的一项重要指标。为了解决牛乳体细胞检查中存在的一些问题，提高乳腺炎诊断的效率核准确率，运用图像特征提取和分类识别技术，对四类牛乳体细胞进行分类识别研究。本文提出基于改进形态特征的体细胞分类识别，首先选取了8类形态特征和4类纹理特征，同时改进了圆形度、矩形度表达公式。最后将特征集输入到随机森林分类器中进行特征匹配。实验证明，改进后的圆形度、矩形度表达式提高了分类的准确率。
Abstract: Milk somatic cell is an important indicator of milk quality assessment and mastitis diagnosis. In order to solve some problems in the examination of bovine milk cells, improve the efficiency and accuracy of mastitis diagnosis, we use the image feature extraction and classification recognition technology to classify and recognise of four kinds of bovine milk cells. An algorithm for recognition of milk body cells based on improved morphological features was proposed. First, we extracted 8 morphological features and 4 texture features, and then improved the circularity, squareness formula. Finally, we put them into Random Forest (RF) for feature matching. The experiments show that improved circularity, squareness expression increase the accuracy of the classification.
文章引用：章潇俪, 薛河儒, 郜晓晶, 周艳青. 基于改进形态特征的牛乳体细胞分类识别算法[J]. 计算机科学与应用, 2018, 8(9): 1354-1363. https://doi.org/10.12677/CSA.2018.89147

参考文献

[1] Cavero, D., Tolle, K.-H., Rave, G., et al. (2007) Analysing Serial Data for Mastitis Detection by Means of Local Regression. Livestock Science, 110, 101-110. [Google Scholar] [CrossRef] 
[2] 薛河儒. 牛乳体细胞彩色图像分割方法的研究[D]: [博士学位论文]. 呼和浩特: 内蒙古农业大学, 2007.
[3] 宋亚攀. 中国奶牛乳房炎防治研究进展[J]. 中国奶牛, 2010(12): 48-53.
[4] Ferrero, F.J., Valledor, M. and Campo, J.C. (2014) Screening Method for Early Detection of Mastitis in Cows. Measure-ment, 47, 855-860. [Google Scholar] [CrossRef] 
[5] 丘通强, 林少宝, 吴焕贞. 鲜牛乳中体细胞数检测方法探讨[J]. 现代食品科技, 2005(21): 158-160.
[6] 郑浩, 高飞, 徐晔, 等. 应用上海乳房炎检测法检测奶牛隐性乳房炎[J]. 畜牧与兽医, 2006, 38(1): 47-48.
[7] Janzekovic, M., Brus, M., Mursec, B., et al. (2009) Mastitis Detection Based on Electric Conductivity of Milk. Journal of Achievements in Materials and Manufacturing Engineering, 34, 39-46.
[8] 宁梓淯, 罗微. 基于细胞核特征的宫颈癌细胞图像的识别与分类[J]. 自动化与仪器仪表, 2016(10): 197-199.
[9] 周颖颖, 周振宇, 孙宁, 等. 基于改进LBP特征的白细胞识别[J]. 生物医学工程研究, 2005, 24(4): 242-246.
[10] Huang, D.C., Hung, K.D. and Chan, Y.K. (2012) A Computer Assisted Method for Leukocyte Nucleus Segmentation and Recognition in Blood Smear Images. Journal of Systems & Soft-ware, 85, 2104-2118. [Google Scholar] [CrossRef] 
[11] 古辉, 吴佳丽. 一种红细胞特征提取与分类识别的研究[J]. 浙江工业大学学报, 2009, 37(5): 480-485.
[12] 胡小峰, 赵辉. Visual C++/MATLAB图像处理与模式识别实用案例精选[M]. 北京: 人民邮电出版社, 2004.
[13] Garcia, G. and Bernussou, J. (1995) Pole Assignment for Uncertain Systems in a Specified Disk by State Feedback. IEEE Transaction on Automatic Control, 40, 184-190.
[14] 韩晓红, 胡彧. Kmean聚类算法的研究[J]. 太原理工大学学报, 2009, 40(3): 236-239.
[15] Haralick, R.M. (2005) Statistical and Structural Approaches to Texture. Proceedings of IEEE, 67, 786-804. [Google Scholar] [CrossRef] 
[16] Ulaby, F.T., Kouyate, F., Brisco, B., et al. (1986) Textural Information in SAR Images. IEEE Transactions on Geoscience and Remote Sensing, 24, 235-245. [Google Scholar] [CrossRef] 
[17] Song, Z.L. and Lu, Z.B. (2007) Algorithm Research of Content Based Image Feature Extraction. The Tenth Academic Annual Conference of the Jiangsu Association for System Engineering.
[18] Li, B.C. (2007) Feature Extraction of Image Zoom Edge Shape. Journal of Kashgar Teachers College, 28, 62-64.
[19] 顾幸方. 基于随机森林的视觉跟踪算法研究及应用[D]: [硕士学位论文]. 南京: 南京理工大学, 2013.
[20] 孙伟. 基于随机森林的乳腺肿瘤细胞细针穿刺辅助诊断[J]. 计算机应用, 2015, 35(S2): 143-145, 169.
[21] 汪庆华, 刘江炜, 张兰兰. 交叉验证K近邻算法分类研究[J]. 西安工业大学学报, 2015(2): 119-124.
[22] 胡局新, 张功杰. 基于K折交叉验证的选择性集成分类算法[J]. 科技通报, 2013(12): 115-117.