<FONT face="Verdana">基于图像的水稻病害识别方法研究 </FONT>

管泽鑫,唐健,杨保军,周营烽,范德耀,姚青,

doi:10.3969/j.issn.1001-7216.2010.05.009

中国水稻科学 >

2010 , Vol. 24 >Issue 5: 497 - 497～502

DOI: https://doi.org/10.3969/j.issn.1001-7216.2010.05.009

研究报告

基于图像的水稻病害识别方法研究

展开

¹浙江理工大学信息电子学院, 浙江杭州 310018； ²中国水稻研究所, 浙江杭州 310006；*通讯联系人, E-mail: q-yao@126.com

收稿日期: 1900-01-01

修回日期: 1900-01-01

网络出版日期: 2010-09-10

收起

Study on Recognition Method of Rice Disease Based on Image

Expand

¹College of Informatics and Electronics, Zhejiang SciTech University, Hangzhou 310018, China; ²China National Rice Research Institute, Hangzhou 310006, China；*Corresponding author, E-mail: q-yao@126.com

Received date: 1900-01-01

Revised date: 1900-01-01

Online published: 2010-09-10

Fold

摘要

利用图像处理技术和贝叶斯判别法对水稻3种常见病害进行识别研究。首先，利用颜色特征与病斑外轮廓分割病斑，提取病斑形态、颜色、纹理特征共63个参数；然后，应用逐步判别分析法对4个不同参数集合筛选最有效识别参数；最后，利用贝叶斯判别法进行分类识别。结果表明，逐步判别法最多可使参数减少到原来的35.2％，识别准确率最高为97.2％。该方法可以应用于其他农作物病害识别。

关键词： 水稻; 病害识别; 图像处理; 逐步判别分析; 贝叶斯判别法

本文引用格式

管泽鑫,唐健,杨保军,周营烽,范德耀,姚青, . 基于图像的水稻病害识别方法研究 [J]. 中国水稻科学, 2010 , 24(5) : 497 -497～502 . DOI: 10.3969/j.issn.1001-7216.2010.05.009

Abstract

The recognition method of three kinds of rice diseases (blast, sheath blight, and bacterial leaf blight) was studied by image processing technique and the Bayes discrimination method. Firstly, the disease spots were segmented by color features and their outlines, and 63 parameters of shape, color and texture features were extracted. Secondly, the stepwise discriminant analysis was used to select effective recognition parameters from four parameter sets of shape, color, texture feature and all of them. Finally, the Bayes discrimination method was applied to classify and recognize the three kinds of rice diseases. The results showed that the number of texture parameters decreased to 35.2% and the highest recognition rates of four parameter sets was 97.2%. This method could also be applied to recognize diseases of other crops.

Key words： rice; diseases recognition; image processing; stepwise discriminant analysis; Bayes discrimination method

参考文献

[1]葛婧, 邵陆寿, 丁克坚, 等. 玉米小斑病病害程度图像检测. 农业机械学报, 2008, 39(1): 114-117.

[2]赵玉霞, 王克如, 白中英, 等. 基于图像识别的玉米叶部病害诊断研究. 中国农业科学, 2007, 40(4): 698-703.

[3]Moshou D, Bravo C, West J, et al. Automatic detection of “yellow rust” in wheat using reflectance measurements and neural networks. Comp & Electron Agric, 2004, 44: 173-188.

[4]毛罕平, 徐贵力, 李萍萍. 基于计算机视觉的番茄营养元素亏缺的识别. 农业机械学报, 2003, 34(2): 73-75.

[5]房俊龙, 张长利, 潘伟, 等. 用遗传算法训练的人工神经网络识别番茄生理病害果. 农业工程学报, 2004, 20(3): 113-116.

[6]熊雪梅, 姬长英. 遗传神经网络在温室黄瓜霜霉病预测中的应用. 农业机械学报, 2002, 33(4): 69-71.

[7]崔艳丽, 程鹏飞, 董晓志, 等. 温室植物病害的图像处理及特征值提取方法的研究——基于色度的特征值提取研究. 农业工程学报, 2005, 21(增): 32-35.

[8]Pydipati R, Burks T F, Lee W S. Identification of citrus disease using color texture features and discriminant analysis. Comp & Electron Agric, 2006, 52： 49-59．

[9]Pydipati R, Burks T F, Lee W S. Statistical and neural network classifiers for citrus disease detection using machine vision. Trans ASAE, 2005, 48(5): 2007-2014.

[10]赵进辉, 罗锡文, 周志艳．基于颜色与形状特征的甘蔗病害图像分割方法．农业机械学报, 2008, 39(9): 100-103.

[11]冯登超, 杨兆选, 乔晓军．基于改进型蚁群算法和Gauss-Markov随机场的植物病斑自适应分割. 沈阳农业大学学报, 2007, 38(3): 391-394.

[12]Tünde Vízhányó, József Felfldi. Enhancing colour differences in images of diseased mushrooms. Comp & Electron Agric, 2000, 26: 187-198.

[13]Sako Y, Emilie E R, Daoust T, et al. Computer image analysis and classification of giant ragweed seeds. Weed Sci, 2001, 49: 738-745.

[14]Granitto P M, Navone H D, Verdes P F, et al. Weed seeds identification by machine vision．Comp & Electron Agric, 2002， 33: 91-103.

[15]Marchant J A, Onyango C M．Comparison of a Bayes classifier with a multilayer feed-forward neural network using the example of plant/weed/soil discrimination. Comp & Electron Agric, 2003， 39： 3-22．

[16]El-Faki M S, Zhang N, Peterson D E. Weed detection using color machine vision. Trans ASAE, 2000, 43(6): 1969-1978．

[17]田有文, 张长水, 李成华. 基于支持向量机和色度矩的植物病害识别研究. 农业机械学报, 2004, 35(3): 95-98.

[18]Gullino M L, Fletcher J, Gamliel A, et al. Crop Biosecurity. Dordrecht: Springer, 2008.

[19]蔡祝男, 吴慰文, 高君川. 水稻病虫害防治. 北京: 金盾出版社, 1992.

[20]Otsu N A. Threshold selection method from gray-level histogram. IEEE Trans Syst Man Cybenet, 1979, 15： 652-655.

[21]Bradski G, Kaehler A. Learning OpenCV: Computer Vision with the OpenCV Library. California: O′Reilly Media Inc., 2008.

[22]李国辉, 柳伟, 曹莉华. 一种基于颜色特征的图像检索方法. 中国图象图形学报, 1999, 4(3): 248-251.

[23]章毓晋. 基于内容的视觉信息检索. 北京: 科学出版社, 2003.

[24]Haralick R M, Shanmugam K, Dinstein I. Textural features for image classification. IEEE Trans Syst Man Cybernet, 1973, 3(6): 610-621.

[25]唐启义, 冯明光．DPS数据处理系统. 北京: 科学出版社, 2007.

[26]边肇祺, 张学工. 模式识别. 北京: 清华大学出版社, 2000.

Options

文章导航

模态框（Modal）标题

摘要

本文引用格式

Abstract

参考文献