赤潮藻显微图像自动识别方法

doi:10.6040/j.issn.1672-3961.2.2015.044

摘要/Abstract

摘要： 利用藻种细胞生物形态差异进行图像分析是浮游生物显微图像识别的一种有效方法,但存在藻种库单一、局部生理特征难以形式化描述等难题。为了克服以上难题,将赤潮藻显微图像识别分解为精确分割、特征提取、特征降维和分类诊断四个渐进识别过程。采用多方向投影积分的方法定位分割出细胞目标,进一步对顶刺和横沟细节区域实现了精细分割;将藻种生理特征与机器识别特征一一对应,依次对形状、不变矩、纹理和局部形态两级特征进行了有效地特征提取和描述;采用支持向量机多类别分类模型进行分类识别。研究结果表明,该方法能准确分割目标,可对不同角度拍摄的15类藻种细胞显微图像完成快速分类。

关键词: 横沟分割, 顶刺分割, 显微图像识别, 生物形态特征

Abstract: At present, the microscopic image identification of harmful algae based on biological morphological features are applied widely. However, there are some challenges, such as limited algae species resources, the difficulty of describing biological detailed features. To solve these problems, the identification of harmful algae was divided into four gradual processes: precise segmentation, feature extraction, feature dimension reduction and classification. First, the method based on projection and integral on multiple directions was proposed to extract cell object, and then the spine and cingulum were extracted. Second, the effective description were proposed after shape features, moment invariants, texture features and domain specific features were extracted. Then, SVM classifier was designed to recognize objects. Experimental results showed that this algorithm could achieve the quicker and better segmentation and recognition of 15 species of algae.

Key words: cingulum segmentation, microscopic image recognition, spine segmentation, biological morphological features

中图分类号:

TP391

乔小燕. 赤潮藻显微图像自动识别方法[J]. 山东大学学报(工学版), 2016, 46(3): 1-6.

QIAO Xiaoyan. Automatic recognition method of microscopic image of harmful algae[J]. JOURNAL OF SHANDONG UNIVERSITY (ENGINEERING SCIENCE), 2016, 46(3): 1-6.

参考文献

[1] 张青田.中国海域赤潮发生趋势的年际变化[J]. 中国环境监测, 2013, 29(5):98-102. ZHANG Qingtian. Review on the annual variation of red tides in china sea[J]. Environmental Monitoring in China, 2013, 29(5):98-102.
[2] 徐海龙, 谷德贤, 张文亮, 等. 基于时间序列的海洋赤潮灾害特征分析[J]. 海洋通报, 2014,33(4):469-474. XU Hailong, GU Dexian, ZHANG Wenliang, et al. Analysis of the red tide features based on time series in the China Sea[J]. Marine Science Bulletin, 2014, 33(4):469-474.
[3] 林风翱, 卢兴旺, 洛昊, 等. 渤海赤潮的历史、现状及其特点[J]. 海洋环境科学, 2008,27(增2):1-5. LIN Fengao, LU Xingwang, LUO Hao, et al. History, status and characteristics of red tide in Bohai Sea[J]. Marine Environmental Science, 2008, 27(supplement 2):1-5.
[4] 洛昊, 马明辉,梁斌, 等. 中国近海赤潮基本特征与减灾对策[J]. 海洋通报, 2013,32(5):595-600. LUO Hao, MA Minghui, LIANG Bin, et al. Basic characteristics and mitigation countermeasures of red tides in China seas[J]. Marine Science Bulletin, 2013, 32(5):595-600.
[5] JEFFREY S Erickson, NASTARAN Hashemi, JAMES M Sullivan, et al. In situ phytoplankton analysis:there's plenty of room at the bottom[J]. Analytical Chemistry, 2012, 84(2):839-850.
[6] CABELL S Davis, FREDRIK T Thwaites, SCOTT M Gallager, et al. A three-axis fast-tow digital video plankton recorder for rapid surveys of plankton taxa and hydrography[J]. Limnology and Oceanography:Methods, 2005, 3:59-74.
[7] HANS Henrik Jakobsen, JACOB Carstensen. FlowCAM:sizing cells and understanding the impact of size distributions on biovolume of planktonic community structure[J]. Aquatic Microbial Ecology, 2011, 65:75-87.
[8] 刘昕, 张俊彬, 黄良民. 流式细胞仪在海洋生物学研究中的应用[J]. 海洋科学, 2007, 31(1):92-96. LIU Xin, ZHANG Junbin, HUANG Liangmin. Applications of flow cytometry(FCM)in researches of marine biology[J]. Marine Sciences, 2007, 31(1):92-96.
[9] Lunven Michel, Lehaitre Michel, Nascimben Eric, et al. A new device for in situ video and fluorescence analysis of marine particles. Applications to phytoplankton studies[J]. Optical Complex Systems, 2013, 24(27):477-478.
[10] 于志刚, 米铁柱, 姚鹏,等. 赤潮藻鉴定与定量检测方法进展[J]. 中国海洋大学学报(自然科学版), 2009, 39(5):1067-1076. YU Zhigang, MI Tiezhu, YAO Peng, et al. Advances in identification and quantification of harmful algae[J]. Periodical of Ocean University of China(Natural Science Edition), 2009, 39(5):1067-1076.
[11] SCHOLIN C A, MARIN R, MILLER P E, et al. Application of DNA probes and a receptor-binding assay for detection of pseudo-nitzschia(bacillariophyceae)species and domoic acid activity in cultured and natural samples[J]. Journal of Phycology, 1999, 35:1356-1367.
[12] 汪世华, 张峰, 袁军,等. 生物毒素检测技术新进展[J]. 应用与环境生物学报, 2008, 14(5):726-731. WANG Shihua, ZHANG Feng, YUAN Jun, et al. Progress of detection technologies for biotoxins[J]. Chinese Journal of Applied and Environmental Biology, 2008, 14(5):726-731.
[13] LAWRENCE J F, MENARD C. Determination of marine toxins by liquid chromatography[J]. Fresenius Journal of Analytical Chemistry, 1991, 339:494-498.
[14] QUILLIAM M A, XIE M, HARDSTAFF W R. Rapid extraction and cleanup for liquid chromatographic determinations of domoic acid in unsalted seafood[J]. Journal of AOAC International, 1995, 78:543-554
[15] JAMES K J, GILLMAN M, LEHANCE M, et al. New fluorimetric method of liquid chromatography for the determination of the neurotoxin domoic acid in seafood and marine phytoplankton[J]. Journal of Chromatography A, 2000, 871(1-2):1-6.
[16] 李鸿宇,张前前,王修林,等. 海洋浮游三维荧光光谱的逐层分类方法研究[J].中国海洋大学学报(自然科学版),2012,42(Z2):117-125. LI Hongyu, ZHANG Qianqian, WANG Xiulin, et al. Tiered classification approach for three-dimentional fluorescent fingerprints of marine phytoplankton[J]. Periodical of Ocean University of China(Natural Science Edition), 2012, 42(Z2):117-125.
[17] 陈纪新, 黄邦欣, 柳欣. 海洋浮游生物原位观测技术研究进展[J]. 地球科学进展, 2013,28(5):572-576. CHEN Jixin, HUANG Bangxin, LIU Xin. The progress of in situ observation of marine plankton[J]. Advances In Earth Science, 2013, 28(5):572-576.
[18] TANG X, LIN F, ANDREW R. Binary plankton image classification[J]. IEEE Journal of Oceanic Engineering, 2006, 31(3):728-735.
[19] 乔小燕. 基于自适应形态学的甲藻显微图像顶刺提取[J]. 中国海洋大学学报(自然科学版), 2013, 43(4):117-122. QIAO Xiaoyan. A method for spine segmentation and feature extraction of pyrrophyta microscopic image[J].Periodical of Ocean University of China(Natural Science Edition), 2012, 43(4):117-122.
[20] 乔小燕. 基于特征灰度和分水岭变换的甲藻横沟区域分割[J]. 计算机科学,2012, 39(6A):555-558. QIAO Xiaoyan. Pyrrophyta spine extraction based on adaptive morphology[J]. Computer Science, 2012, 39(6A):555-558.
[21] HU M K. Visual pattern recognition by moment invariants[J]. IRE Transaction Information Theory, 1962, 8(2):179-187.
[22] 高程程, 惠晓威. 基于灰度共生矩阵的纹理特征提取[J].计算机系统应用, 2010, 19(6):195-198. GAO Chengcheng, HUI Xiaowei. GLCM-based texture feature extraction[J]. Computer System and Applications, 2010, 19(6):195-198.
[23] 丁世飞, 齐丙娟, 谭红艳. 支持向量机理论与算法研究综述[J]. 电子科技大学学报, 2001, 40(1):2-10. DING Shifei, QI Bingjuan, TAN Hongyan. An overview on theory and algorithm of support vector machines[J]. Journal of University of Electronic Science and Technology of China, 2001, 40(1):2-10.
[24] CRISTININI N, TAYLOR J S.支持向量机导论[M]. 李国正,王猛,曾华军,译. 北京:电子工业出版社,2004. CRISTININI N, TAYLOR J S. An introduction to support vector maines and other kernel-based learning methods[M]. LI Guozheng, WANG Meng, Zeng Huajun, trans. Beijing:Publishing House of Electronics Industry, 2004.
[25] VAPNIK V N. Statistical learning theory[M]. New York:Wiley-Interscience, 1998.
[26] 张学工. 关于统计学习理论与支持向量机[J]. 自动化学报,2000,26(1):32-41. ZHANG Xuegong. Statistical learning theory and support vector machines[J]. Acta Automatica Sinica, 2000, 26(1):32-41.
[27] BOSER B E, GUYON I M, VAPNIK V N. A training algorithm for optimal margin classifiers[C] //Proceedings of the Fifth Annual Workshop on Computational Learning Theory. New York:ACM Press, 1992:144-152.

多维度评价

Viewed

Full text

Abstract

Cited

Shared

Discussed