基于HOG特征的IKSVM稻瘟病孢子检测
|
摘要
为解决稻瘟病孢子的人工检测过程中主观性强、自动化程度低、效率低等问题,提出一种基于梯度方向直方图特征(HOG特征)的加性交叉核支持向量机(IKSVM)的稻瘟病孢子检测方法。该方法首先利用图像采集系统采集稻瘟病孢子图像,利用Gamma校正法调节图像的对比度,抑制噪声干扰;然后,提取孢子图像的HOG特征作为输入向量,输入到支持向量机中,构建加性交叉核支持向量机分类器;最后,通过训练得到稻瘟病孢子分类器。为测试所提出的HOG/IKSVM方法的综合性能,分别选用HOG/线性SVM方法与HOG/径向基核SVM(HOG/RBFSVM)方法做对比试验。试验结果表明,HOG/IKSVM的检测率为98. 2%,高于HOG/线性SVM方法的79%;在平均检测时间上,HOG/IKSVM方法的平均检测耗时仅为HOG/RBF-SVM方法的1. 1%。说明该方法可以进行稻瘟病孢子室内检测识别。
In order to solve the disadvantages such as strong subjectivity,low automation and low efficiency of spores detection in rice blast,an additive intersection kernel support vector machine(IKSVM) based on histogram of oriented gradient feature(HOG feature) was proposed to detect rice blast spores. Firstly,the image acquisition system was used to collect spores images of rice blast disease,and Gamma correction was used to adjust the contrast of the images to suppress noise interference.Secondly,the HOG feature of the spores image was extracted as input vectors and input into the support vector machine to construct the intersection kernel support vector machine classifier. Finally,the rice blast spores classifier was obtained by training. In order to test the comprehensive performance of proposed HOG/IKSVM,the HOG/linear SVM method and the HOG/radial basis function kernel SVM(RBF-SVM) method were used for the comparison test. The test results showed that the detection rate of HOG/IKSVM was 98. 2%,which was higher than the 79% of the HOG/linear SVM method. On average detection time,the average detection time of HOG/IKSVM was only 1. 1% of the HOG/RBF-SVM method. This method can be used as a rapid and accurate identification method for indoor detection of rice blast.
In order to solve the disadvantages such as strong subjectivity,low automation and low efficiency of spores detection in rice blast,an additive intersection kernel support vector machine(IKSVM) based on histogram of oriented gradient feature(HOG feature) was proposed to detect rice blast spores. Firstly,the image acquisition system was used to collect spores images of rice blast disease,and Gamma correction was used to adjust the contrast of the images to suppress noise interference.Secondly,the HOG feature of the spores image was extracted as input vectors and input into the support vector machine to construct the intersection kernel support vector machine classifier. Finally,the rice blast spores classifier was obtained by training. In order to test the comprehensive performance of proposed HOG/IKSVM,the HOG/linear SVM method and the HOG/radial basis function kernel SVM(RBF-SVM) method were used for the comparison test. The test results showed that the detection rate of HOG/IKSVM was 98. 2%,which was higher than the 79% of the HOG/linear SVM method. On average detection time,the average detection time of HOG/IKSVM was only 1. 1% of the HOG/RBF-SVM method. This method can be used as a rapid and accurate identification method for indoor detection of rice blast.
引文
1 DEEPTI S,SHAMIM.Current status of conventional and molecular interventions for blast resistance in rice[J].Rice Science,2017,24(6):299-321.
2李成云,陈宗麒,陈琼珠.稻瘟病菌的研究进展[J].西南农业学报,1995,8(3):107-112.LI Chengyun,CHEN Zongqi,CHEN Qiongzhu.Curret studies on rice blast fungi[J].Southwest China Journal of Agricultural Sciences,1995,8(3):107-112.(in Chinese)
3冉莉,朱紫薇,杨超,等.吐温-20和吐温-80对稻瘟病菌孢子萌发的影响[J].西南农业学报,2016,29(10):2379-2382.RAN Li,ZHU Ziwei,YANG Chao,et al.Effects of tween-20 and tween-80 on germination of magnaporthe oryzae spores[J].Southwest China Journal of Agricultural Sciences,2016,29(10):2379-2382.(in Chinese)
4 TALBOT N J.On the trail of a cereal killer:exploring the biology of magnaporthe grisea.[J].Annual Review of Microbiology,2003,57(1):177-202.
5方福平,程式华.论中国水稻生产能力[J].中国水稻科学,2009,23(6):559-566.FANG Fuping,CHENG Shihua.Rice production capacity in China[J].Chinese Journal of Rice Science,2009,23(6):559-566.(in Chinese)
6孙国昌,杜新法,陶荣祥,等.水稻稻瘟病防治策略和21世纪研究展望[J].植物病理学报,1998,28(4):289-292.SUN Guochang,DU Xinfa,TAO Rongxiang,et al.Control tactics and prospect of rice blast research in 21th century[J].Acta Phtyopathologica Sinica,1998,28(4):289-292.(in Chinese)
7杨燕.基于高光谱成像技术的水稻稻瘟病诊断关键技术研究[D].杭州:浙江大学,2012.YANG Yan.The key diagnosis technology of rice blast based on hyper-spectral image[D].Hangzhou:Zhejiang University,2012.(in Chinese)
8王宇新.基于特征分布的图像识别方法研究与应用[D].大连:大连理工大学,2012.WANG Yuxin.Research and application of image recognition method based on visual feature distribution[D].Dalian:Dalian University of Technology,2012.(in Chinese)
9 CHESMORE D,BERNARDT,INMAN A J,et al.Image analysis for the identification of the quarantine pest Tilletia indica[J].Eppo Bulletin,2003,33(3):495-499.
10齐龙,蒋郁,李泽华,等.基于显微图像处理的稻瘟病菌孢子自动检测与计数方法[J].农业工程学报,2015,31(12):186-193.QI Long,JIANG Yu,LI Zehua,et al.Automatic detection and counting method for spores of rice blast based on micro image processing[J].Transactions of the CSAE,2015,31(12):186-193.(in Chinese)
11张荣标,黄义振,孙晓军,等.基于图像处理的圆褐固氮菌浓度快速检测方法[J/OL].农业机械学报,2012,43(10):174-178.http:∥www.j-csam.org/jcsam/ch/reader/view_abstract.aspx?flag=1&file_no=20121031&journal_id=jcsam.DOI:10.6041/j.issn.1000-1298.2012.10.031.ZHANG Rongbiao,HUANG Yizhen,SUN Xiaojun,et al.Rapid detection of azotobacter chroococcum concentration based on image processing[J/OL].Transactions of the Chinese Society for Agricultural Machinery,2012,43(10):174-178.(in Chinese)
12任彧,顾成成.基于HOG特征和SVM的手势识别[J].科技通报,2011,27(2):211-214.REN Yu,GU Chengcheng.Hand gesture recognition based on HOG characters and SVM[J].Bulletin of Science and Technology,2011,27(2):211-214.(in Chinese)
13孙锐,陈军,高隽.基于显著性检测与HOG-NMF特征的快速行人检测方法[J].电子与信息学报,2013,35(8):1921-1926.SUN Rui,CHEN Jun,GAO Jun.Fast pedestrian detection based on saliency detection and HOG-NMF features[J].Journal of Electronics&Information Technology,2013,35(8):1921-1926.(in Chinese)
14 DALAL N,TRIGGS B.Histograms of oriented gradients for human detection[C]∥IEEE Computer Society Conference on Computer Vision&Pattern Recognition.IEEE Computer Society,2005:886-893.
15项磊,徐军.基于HOG特征和滑动窗口的乳腺病理图像细胞检测[J].山东大学学报(工学版),2015,45(1):37-44.XIANG Lei,XU Jun.Nuclei detection of breast histopathology based on HOG feature and sliding window[J].Journal of Shandong University(Engineering Science),2015,45(1):37-44.(in Chinese)
16吴鑫,王桂英,丛杨.基于颜色和深度信息融合的目标识别方法[J].农业工程学报,2013,29(增刊):96-100.WU Xin,WANG Guiying,CONG Yang.Object recognition method by combining color and depth information[J].Transactions of the CSAE,2013,29(Supp.):96-100.(in Chinese)
17童莹.基于空间多尺度HOG特征的人脸表情识别方法[J].计算机工程与设计,2014(11):3918-3922,3979.TONG Ying.Facial expression recognition algoritlzrn based on spatial multi-scaled HOG feature[J].Computer Engineering and Design,2014(11):3918-3922,3979.(in Chinese)
18 MAJI S,BERG A C,MALIK J.Classification using intersection kernel support vector machines is efficient[C]∥Computer Vision and Pattern Recognition,2008.CVPR 2008.IEEE Conference on.IEEE,2008:1-8.
19王旭凤.基于可加性核的快速支持向量机分类算法的研究[D].西安:西安电子科技大学,2017.WANG Xufeng.Fast support vector machines classification algorithm with additive kernel[D].Xi'an:Xidian University,2017.(in Chinese)
20魏丽冉,岳峻,李振波,等.基于核函数支持向量机的植物叶部病害多分类检测方法[J/OL].农业机械学报,2017,48(增刊):166-171.http:∥www.j-csam.org/jcsam/ch/reader/view_abstract.aspx?file_no=2017s027&flag=1.DOI:10.6041/j.issn.1000-1298.2017.S0.027.WEI Liran,YUE Jun,LI Zhenbo,et al.Multi-classification detection method of plant leaf disease based on kernel function SVM[J/OL].Transactions of the Chinese Society for Agricultural Machinery,2017,48(Supp.):166-171.(in Chinese)
2李成云,陈宗麒,陈琼珠.稻瘟病菌的研究进展[J].西南农业学报,1995,8(3):107-112.LI Chengyun,CHEN Zongqi,CHEN Qiongzhu.Curret studies on rice blast fungi[J].Southwest China Journal of Agricultural Sciences,1995,8(3):107-112.(in Chinese)
3冉莉,朱紫薇,杨超,等.吐温-20和吐温-80对稻瘟病菌孢子萌发的影响[J].西南农业学报,2016,29(10):2379-2382.RAN Li,ZHU Ziwei,YANG Chao,et al.Effects of tween-20 and tween-80 on germination of magnaporthe oryzae spores[J].Southwest China Journal of Agricultural Sciences,2016,29(10):2379-2382.(in Chinese)
4 TALBOT N J.On the trail of a cereal killer:exploring the biology of magnaporthe grisea.[J].Annual Review of Microbiology,2003,57(1):177-202.
5方福平,程式华.论中国水稻生产能力[J].中国水稻科学,2009,23(6):559-566.FANG Fuping,CHENG Shihua.Rice production capacity in China[J].Chinese Journal of Rice Science,2009,23(6):559-566.(in Chinese)
6孙国昌,杜新法,陶荣祥,等.水稻稻瘟病防治策略和21世纪研究展望[J].植物病理学报,1998,28(4):289-292.SUN Guochang,DU Xinfa,TAO Rongxiang,et al.Control tactics and prospect of rice blast research in 21th century[J].Acta Phtyopathologica Sinica,1998,28(4):289-292.(in Chinese)
7杨燕.基于高光谱成像技术的水稻稻瘟病诊断关键技术研究[D].杭州:浙江大学,2012.YANG Yan.The key diagnosis technology of rice blast based on hyper-spectral image[D].Hangzhou:Zhejiang University,2012.(in Chinese)
8王宇新.基于特征分布的图像识别方法研究与应用[D].大连:大连理工大学,2012.WANG Yuxin.Research and application of image recognition method based on visual feature distribution[D].Dalian:Dalian University of Technology,2012.(in Chinese)
9 CHESMORE D,BERNARDT,INMAN A J,et al.Image analysis for the identification of the quarantine pest Tilletia indica[J].Eppo Bulletin,2003,33(3):495-499.
10齐龙,蒋郁,李泽华,等.基于显微图像处理的稻瘟病菌孢子自动检测与计数方法[J].农业工程学报,2015,31(12):186-193.QI Long,JIANG Yu,LI Zehua,et al.Automatic detection and counting method for spores of rice blast based on micro image processing[J].Transactions of the CSAE,2015,31(12):186-193.(in Chinese)
11张荣标,黄义振,孙晓军,等.基于图像处理的圆褐固氮菌浓度快速检测方法[J/OL].农业机械学报,2012,43(10):174-178.http:∥www.j-csam.org/jcsam/ch/reader/view_abstract.aspx?flag=1&file_no=20121031&journal_id=jcsam.DOI:10.6041/j.issn.1000-1298.2012.10.031.ZHANG Rongbiao,HUANG Yizhen,SUN Xiaojun,et al.Rapid detection of azotobacter chroococcum concentration based on image processing[J/OL].Transactions of the Chinese Society for Agricultural Machinery,2012,43(10):174-178.(in Chinese)
12任彧,顾成成.基于HOG特征和SVM的手势识别[J].科技通报,2011,27(2):211-214.REN Yu,GU Chengcheng.Hand gesture recognition based on HOG characters and SVM[J].Bulletin of Science and Technology,2011,27(2):211-214.(in Chinese)
13孙锐,陈军,高隽.基于显著性检测与HOG-NMF特征的快速行人检测方法[J].电子与信息学报,2013,35(8):1921-1926.SUN Rui,CHEN Jun,GAO Jun.Fast pedestrian detection based on saliency detection and HOG-NMF features[J].Journal of Electronics&Information Technology,2013,35(8):1921-1926.(in Chinese)
14 DALAL N,TRIGGS B.Histograms of oriented gradients for human detection[C]∥IEEE Computer Society Conference on Computer Vision&Pattern Recognition.IEEE Computer Society,2005:886-893.
15项磊,徐军.基于HOG特征和滑动窗口的乳腺病理图像细胞检测[J].山东大学学报(工学版),2015,45(1):37-44.XIANG Lei,XU Jun.Nuclei detection of breast histopathology based on HOG feature and sliding window[J].Journal of Shandong University(Engineering Science),2015,45(1):37-44.(in Chinese)
16吴鑫,王桂英,丛杨.基于颜色和深度信息融合的目标识别方法[J].农业工程学报,2013,29(增刊):96-100.WU Xin,WANG Guiying,CONG Yang.Object recognition method by combining color and depth information[J].Transactions of the CSAE,2013,29(Supp.):96-100.(in Chinese)
17童莹.基于空间多尺度HOG特征的人脸表情识别方法[J].计算机工程与设计,2014(11):3918-3922,3979.TONG Ying.Facial expression recognition algoritlzrn based on spatial multi-scaled HOG feature[J].Computer Engineering and Design,2014(11):3918-3922,3979.(in Chinese)
18 MAJI S,BERG A C,MALIK J.Classification using intersection kernel support vector machines is efficient[C]∥Computer Vision and Pattern Recognition,2008.CVPR 2008.IEEE Conference on.IEEE,2008:1-8.
19王旭凤.基于可加性核的快速支持向量机分类算法的研究[D].西安:西安电子科技大学,2017.WANG Xufeng.Fast support vector machines classification algorithm with additive kernel[D].Xi'an:Xidian University,2017.(in Chinese)
20魏丽冉,岳峻,李振波,等.基于核函数支持向量机的植物叶部病害多分类检测方法[J/OL].农业机械学报,2017,48(增刊):166-171.http:∥www.j-csam.org/jcsam/ch/reader/view_abstract.aspx?file_no=2017s027&flag=1.DOI:10.6041/j.issn.1000-1298.2017.S0.027.WEI Liran,YUE Jun,LI Zhenbo,et al.Multi-classification detection method of plant leaf disease based on kernel function SVM[J/OL].Transactions of the Chinese Society for Agricultural Machinery,2017,48(Supp.):166-171.(in Chinese)