基于分形维数的叶片识别方法研究
|
摘要
我国是林业大国,拥有丰富的林业物种资源,随着环境问题的日益突出,濒危植物的数量激增,又由于人工识别具有效率低、主观性强的缺点,因此,基于计算机技术的植物物种识别具有重要的研究意义。叶片是植物形态结构的重要组成部分,不同植物拥有不同的形状和纹理特征,将其作为林种识别的依据具有很高的准确率。
本文首先介绍了分形理论的相关知识,包括分形的定义,不同的测定方法以及如何将分形维数作为纹理特征。接着介绍了特征提取、主成分分析等图像识别所需要的技术。接着具体介绍了基于分形理论的叶片图像识别方法,在经过图像预处理后选取了21维形态和纹理特征,并选取前10个主成分来表示原图像的信息,然后采用SVM分类器进行植物叶片分类。最后对26种叶片(390幅图像)的图像库进行实验,实验结果证明分形维数作为纹理特征的方法能够提高叶片识别的准确率,为实际应用提供了新的思路。
Our country owns a large number of plant species and is rich in forest. As environment problem rises, the number of endangered plant is increasing greatly. And the low efficiency and high subjectivity of manual recognition are great defect to plant recognition. Because of all of these, the study of plant recognition technique which is based on computer has important significance. Leaf is an essential part of plant. Different plant has leaves with different shape and texture features, according to these features we can recognize plant species with high accuracy.
In this paper, the knowledge of fractal theory is introduced firstly, including the definition and different measure method of fractal and how the fractal can be used as texture feature. Next the technique which is necessary in image recognition is presented, such as feature extraction, principal component analysis and so on. And then the method of leaves recognition based on fractal dimension is implemented.21-dimensional shape and texture features is chosen after image pre-process and select the top 10 principal component to represent leaf image. Then SVM classifier is used to classify the leaves images. Finally, the experiment tested on 390 images which belong to 26 kinds of leaves. The result of experiment proves that fractal dimension which is used as texture feature can increase recognition accuracy. This method provides new way to certain utility value.
本文首先介绍了分形理论的相关知识,包括分形的定义,不同的测定方法以及如何将分形维数作为纹理特征。接着介绍了特征提取、主成分分析等图像识别所需要的技术。接着具体介绍了基于分形理论的叶片图像识别方法,在经过图像预处理后选取了21维形态和纹理特征,并选取前10个主成分来表示原图像的信息,然后采用SVM分类器进行植物叶片分类。最后对26种叶片(390幅图像)的图像库进行实验,实验结果证明分形维数作为纹理特征的方法能够提高叶片识别的准确率,为实际应用提供了新的思路。
Our country owns a large number of plant species and is rich in forest. As environment problem rises, the number of endangered plant is increasing greatly. And the low efficiency and high subjectivity of manual recognition are great defect to plant recognition. Because of all of these, the study of plant recognition technique which is based on computer has important significance. Leaf is an essential part of plant. Different plant has leaves with different shape and texture features, according to these features we can recognize plant species with high accuracy.
In this paper, the knowledge of fractal theory is introduced firstly, including the definition and different measure method of fractal and how the fractal can be used as texture feature. Next the technique which is necessary in image recognition is presented, such as feature extraction, principal component analysis and so on. And then the method of leaves recognition based on fractal dimension is implemented.21-dimensional shape and texture features is chosen after image pre-process and select the top 10 principal component to represent leaf image. Then SVM classifier is used to classify the leaves images. Finally, the experiment tested on 390 images which belong to 26 kinds of leaves. The result of experiment proves that fractal dimension which is used as texture feature can increase recognition accuracy. This method provides new way to certain utility value.
引文
[1]我国有近2000种野生动植物物种濒临灭绝[z].2010.
[2]Andrewr英.统计模式识别[M].北京：电子工业出版社,2004.
[3]Kennethfalconer著英,曾文曲译.分形几何[M].北京：人民邮电出版社,2007：303.
[4]Kennethj英肯尼思·法尔科内.分形几何中的技巧[M].沈阳：东北大学出版社,1999：323.
[5]Nellocristianini英,Johnshawe-Taylor著英,李国正等译.支持向量机导论[M].北京：电子工业出版社,2004.
[6]杜吉祥.植物物种机器识别技术的研究[D].中国科学技术大学,2005.
[7]杜吉祥,汪增福.基于径向基概率神经网络的植物叶片自动识别方法[J].模式识别与人工智能.2008(2)：206-213.
[8]范立南,韩晓微,张广渊著.图像处理与模式识别[M].北京：科学出版社,2007：235.
[9]傅弘,池哲儒,常杰,等.基于人工神经网络的叶脉信息提取——植物活体机器识别研究Ⅰ[J].植物学通报.2004(4)：429-436.
[10]贺鹏,黄林.植物叶片特征提取及识别[J].农机化研究.2008(6)：168-170.
[11]侯铜,姚立红,阚江明.基于叶片外形特征的植物识别研究[J].湖南农业科学.2009(4)：123-125.
[12]胡玉薇.基于分形理论的水声图像分割与识别[D].哈尔滨工程大学,2009.
[13]黄晶.基于分形维度与灰度共生矩阵的图像分类研究[D].武汉理工大学,2008.
[14]阚江明,王怡萱,杨晓微,等.基于叶片图像的植物识别方法[J].科技导报.2010(23)：81-85.
[15]李宏贵,李兴国,李国桢,等.基于分形特征的红外图像识别方法[J].红外与激光工程.1999(1).
[16]李厚强,刘政凯,林峰.基于分形理论的航空图像分类方法[J].遥感学报.2001(5)：353-357.
[17]李水根编著.分形[M].北京：高等教育出版社,2004：235.
[18]刘明芹,张晓光.一种计算图像分形维数的有效方法[J].西安科技大学学报.2009(3)：369-373.
[19]刘文萍,张常年,赵会群,等.一种基于分形特征的图片分类算法[J].中国图象图形学报.2005(6)：754-757.
[20]刘卓夫,桑恩方.基于分形理论的声纳图像识别[J].微机发展.2004(4)：55-57.
[21]马莉,范影乐著.纹理图像分析[M].北京：科学出版社,2009：231.
[22]聂笃宪,曾文曲,易珺.基于布朗模型和小波变换的图像分形维数计算[J].电脑知识与技术.2006(23)：124-133.
[23]彭瑞东,谢和平,鞠杨.二维数字图像分形维数的计算方法[J].中国矿业大学学报.2004(1).
[24]祁亨年,寿韬,金水虎.基于叶片特征的计算机辅助植物识别模型[J].浙江林学院学报.2003(3).
[25]孙永新.基于多尺度形状分析的叶形识别系统[J].计算机应用.2009(6)：1707-1710.
[26]田村秀行编著日,金喜子,乔双译.计算机图像处理[M].北京：科学出版社,2004.
[27]王丹青.基于分形理论的大气悬浮颗粒物图像识别[D].武汉理工大学,2006.
[28]王立臣,淮永建,杨刚,等.虚拟植物叶片的可视化建模技术研究[J].计算机仿真.2010(5)：204-208.
[29]王晓峰,黄德双,杜吉祥,等.叶片图像特征提取与识别技术的研究[J].计算机工程与应用. 2006(3)：190-193.
[30]魏旭.基于主成分分析的特征融合及其应用[D].电子科技大学,2008.
[31]吴高洪,章毓晋,林行刚.基于分形的自然纹理自相关描述和分类[J].清华大学学报(自然科学版).2000a(3)：90-93.
[32]吴清锋.基于内容的中草药植物图像检索关键技术研究[D].厦门大学,2007.
[33]肖鹏.基于分形维数的纹理图像分割[D].西安电子科技大学,2010a.
[34]闫敬文著.数字图像处理[M].北京：国防工业出版社,2007：310.
[35]杨辉军,陈立伟.基于分形特征的植物识别[J].计算机工程与设计.2010(24)：5321-5323.
[36]杨会云,张有会,霍利岭,等Bayes理论和邻域平均法在图像去噪中的应用[J].计算机工程与应用.2010(9)：149-151.
[37]杨杰.数字图像处理及MATLAB实现[M].北京：电子工业出版社,2010：267.
[38]杨书申,邵龙义MATLAB环境下图像分形维数的计算[J].中国矿业大学学报.2006(4)：478-482.
[39]游文杰,吉国力,袁明顺.高维少样本数据的特征压缩[J].计算机工程与应用.2009(36)：165-169.
[40]于兴华,傅星,卢汉清,罗曼丽,曹伟.应用计算机进行植物自动分类的初步研究[J].生态学杂志.1994(2).
[41]翟传敏,杜吉祥.基于形状上下文特征的植物叶图像匹配方法[J].广西师范大学学报(自然科学版).2009(3)：171-174.
[42]张济忠编著.分形[M].北京：清华大学出版社,2011：310.
[43]张善文,黄德双.一种鲁棒的监督流形学习算法及其在植物叶片分类中的应用[J].模式识别与人工智能.2010(6)：836-841.
[44]张涛,孙林,黄爱民.图像分形维数的差分盒方法的改进研究[J].电光与控制.2007(5)：55-57.
[45]张志三著.漫谈分形=Atalkaboutfractals[M]长沙：湖南教育出版社,1993：150.
[46]朱荣胜,陈庆山,杨佳,等.大豆叶片的特征提取方法研究[J].农机化研究.2010(5)：13-16.
[47]Abbasi S, Mokhtarian F, Kittler J. Reliable classification of chrysanthemum leaves through Curvature Scale Space[M]. Scale-Space Theory in Computer Vision, ter Haar Romeny B, Florack L, Koenderink J, et al, Springer Berlin/Heidelberg,1997:1252,284.
[48]Chen C C. Improved moment invariants for shape discrimination[J]. Pattern Recognition.1993, 26(5):683-686.
[49]Guyer D E, Miles G E. Application of Machine Vision to Shape Analysis in Leaf and Plant Identification[J].1993,36(1):163-171.
[50]Guyer D E, Miles G E, Schreiber M M. Machine Vision and Image Processing for Plant Identification[J]. Transactions of the ASAE.1986:1500-1507.
[51]Hu M. Visual pattern recognition by moment invariants[J]. IEEE Trans on Information Theory. 1962,8(2):179-187.
[52]Lee C, Chen S. Classification of leaf images[J]. International Journal of Imaging Systems and Technology.2006,16(1):15-23.
[53]Li Z, An Q, Ji C. CLASSIFICATION OF WEED SPECIES USING ARTIFICIAL NEURAL NETWORKS BASED ON COLOR LEAF TEXTURE FEATURE[M]. Computer and Computing Technologies in Agriculture Ⅱ, Volume 2, Zhao C, Li D, Springer Boston,2009:294,1217.
[54]Liu J, Zhang S, Deng S. A Method of Plant Classification Based on Wavelet Transforms and Support Vector Machines[M]. Emerging Intelligent Computing Technology and Applications, Huang D, Jo K, Lee H, et al, Springer Berlin/Heidelberg,2009:5754,253.
[55]Mcdonald T, Chen Y R. Application of morphological image processing in agriculture[J]. Transactions of the ASAE.1990,33(4):1345-1352.
[56]Nam Y, Hwang E. A Shape-Based Retrieval Scheme for Leaf Images[M]. Advances in Multimedia Information Processing-PCM 2005, Ho Y, Kim H, Springer Berlin/Heidelberg,2005:3767,876.
[57]Nam Y, Hwang E, Kim D. CLOVER:A Mobile Content-Based Leaf Image Retrieval System[M]. Digital Libraries:Implementing Strategies and Sharing Experiences, Fox E, Neuhold E, Premsmit P, et al, Springer Berlin/Heidelberg,2005:3815,139.
[58]Nam Y, Hwang E, Kim D. A similarity-based leaf image retrieval scheme Joining shape and venation features[J].110(2).2008:245-259.
[59]Oide M, Ninomiya S. Matching Shape with Self-Intersection:Application to Leaf Classification[J]. IEEE Trans on Image Processing.2004,13(5):653-661.
[60]Park J, Hwang E, Nam Y. A Venation-Based Leaf Image Classification Scheme[M]. Information Retrieval Technology, Ng H, Leong M, Kan M, et al, Springer Berlin/Heidelberg,2006:4182,416.
[61]Sarkar N, Chaudhuri B B. An efficient differential box-counting approach to compute fractal dimension of image[J]. IEEE Trans. On SMC.1994,24(1):115-120.
[62]Shearer S A, Holmes R G. Plant identification using color color-occurrence matrices[J]. Transactions of the ASAE.1990,33(6):2037-2044.
[63]Timmermans A J M, Hulzebosch A A. Computer vision system for on-line sorting of pot plants using an artificial neural network classifier[J].1996,15(1):41-55.
[64]Tomasi C, Manduchi R. Bilateral filtering for gray and color images:Proceedings of the IEEE International Conference on Computer Vision[Z]. Bombay, India:1998839-846.
[65]Tricot C. Curves and Fractal Dimension[M]. New York:Springer-Verlag,1995.
[66]Yonekawa S, Sakai N, Kitani O. Identification of idealized leaf types using simple dimensionless shape factors by image analysis[J]. Trans of the ASAE.1996,39(4):1525-1533.
[2]Andrewr英.统计模式识别[M].北京：电子工业出版社,2004.
[3]Kennethfalconer著英,曾文曲译.分形几何[M].北京：人民邮电出版社,2007：303.
[4]Kennethj英肯尼思·法尔科内.分形几何中的技巧[M].沈阳：东北大学出版社,1999：323.
[5]Nellocristianini英,Johnshawe-Taylor著英,李国正等译.支持向量机导论[M].北京：电子工业出版社,2004.
[6]杜吉祥.植物物种机器识别技术的研究[D].中国科学技术大学,2005.
[7]杜吉祥,汪增福.基于径向基概率神经网络的植物叶片自动识别方法[J].模式识别与人工智能.2008(2)：206-213.
[8]范立南,韩晓微,张广渊著.图像处理与模式识别[M].北京：科学出版社,2007：235.
[9]傅弘,池哲儒,常杰,等.基于人工神经网络的叶脉信息提取——植物活体机器识别研究Ⅰ[J].植物学通报.2004(4)：429-436.
[10]贺鹏,黄林.植物叶片特征提取及识别[J].农机化研究.2008(6)：168-170.
[11]侯铜,姚立红,阚江明.基于叶片外形特征的植物识别研究[J].湖南农业科学.2009(4)：123-125.
[12]胡玉薇.基于分形理论的水声图像分割与识别[D].哈尔滨工程大学,2009.
[13]黄晶.基于分形维度与灰度共生矩阵的图像分类研究[D].武汉理工大学,2008.
[14]阚江明,王怡萱,杨晓微,等.基于叶片图像的植物识别方法[J].科技导报.2010(23)：81-85.
[15]李宏贵,李兴国,李国桢,等.基于分形特征的红外图像识别方法[J].红外与激光工程.1999(1).
[16]李厚强,刘政凯,林峰.基于分形理论的航空图像分类方法[J].遥感学报.2001(5)：353-357.
[17]李水根编著.分形[M].北京：高等教育出版社,2004：235.
[18]刘明芹,张晓光.一种计算图像分形维数的有效方法[J].西安科技大学学报.2009(3)：369-373.
[19]刘文萍,张常年,赵会群,等.一种基于分形特征的图片分类算法[J].中国图象图形学报.2005(6)：754-757.
[20]刘卓夫,桑恩方.基于分形理论的声纳图像识别[J].微机发展.2004(4)：55-57.
[21]马莉,范影乐著.纹理图像分析[M].北京：科学出版社,2009：231.
[22]聂笃宪,曾文曲,易珺.基于布朗模型和小波变换的图像分形维数计算[J].电脑知识与技术.2006(23)：124-133.
[23]彭瑞东,谢和平,鞠杨.二维数字图像分形维数的计算方法[J].中国矿业大学学报.2004(1).
[24]祁亨年,寿韬,金水虎.基于叶片特征的计算机辅助植物识别模型[J].浙江林学院学报.2003(3).
[25]孙永新.基于多尺度形状分析的叶形识别系统[J].计算机应用.2009(6)：1707-1710.
[26]田村秀行编著日,金喜子,乔双译.计算机图像处理[M].北京：科学出版社,2004.
[27]王丹青.基于分形理论的大气悬浮颗粒物图像识别[D].武汉理工大学,2006.
[28]王立臣,淮永建,杨刚,等.虚拟植物叶片的可视化建模技术研究[J].计算机仿真.2010(5)：204-208.
[29]王晓峰,黄德双,杜吉祥,等.叶片图像特征提取与识别技术的研究[J].计算机工程与应用. 2006(3)：190-193.
[30]魏旭.基于主成分分析的特征融合及其应用[D].电子科技大学,2008.
[31]吴高洪,章毓晋,林行刚.基于分形的自然纹理自相关描述和分类[J].清华大学学报(自然科学版).2000a(3)：90-93.
[32]吴清锋.基于内容的中草药植物图像检索关键技术研究[D].厦门大学,2007.
[33]肖鹏.基于分形维数的纹理图像分割[D].西安电子科技大学,2010a.
[34]闫敬文著.数字图像处理[M].北京：国防工业出版社,2007：310.
[35]杨辉军,陈立伟.基于分形特征的植物识别[J].计算机工程与设计.2010(24)：5321-5323.
[36]杨会云,张有会,霍利岭,等Bayes理论和邻域平均法在图像去噪中的应用[J].计算机工程与应用.2010(9)：149-151.
[37]杨杰.数字图像处理及MATLAB实现[M].北京：电子工业出版社,2010：267.
[38]杨书申,邵龙义MATLAB环境下图像分形维数的计算[J].中国矿业大学学报.2006(4)：478-482.
[39]游文杰,吉国力,袁明顺.高维少样本数据的特征压缩[J].计算机工程与应用.2009(36)：165-169.
[40]于兴华,傅星,卢汉清,罗曼丽,曹伟.应用计算机进行植物自动分类的初步研究[J].生态学杂志.1994(2).
[41]翟传敏,杜吉祥.基于形状上下文特征的植物叶图像匹配方法[J].广西师范大学学报(自然科学版).2009(3)：171-174.
[42]张济忠编著.分形[M].北京：清华大学出版社,2011：310.
[43]张善文,黄德双.一种鲁棒的监督流形学习算法及其在植物叶片分类中的应用[J].模式识别与人工智能.2010(6)：836-841.
[44]张涛,孙林,黄爱民.图像分形维数的差分盒方法的改进研究[J].电光与控制.2007(5)：55-57.
[45]张志三著.漫谈分形=Atalkaboutfractals[M]长沙：湖南教育出版社,1993：150.
[46]朱荣胜,陈庆山,杨佳,等.大豆叶片的特征提取方法研究[J].农机化研究.2010(5)：13-16.
[47]Abbasi S, Mokhtarian F, Kittler J. Reliable classification of chrysanthemum leaves through Curvature Scale Space[M]. Scale-Space Theory in Computer Vision, ter Haar Romeny B, Florack L, Koenderink J, et al, Springer Berlin/Heidelberg,1997:1252,284.
[48]Chen C C. Improved moment invariants for shape discrimination[J]. Pattern Recognition.1993, 26(5):683-686.
[49]Guyer D E, Miles G E. Application of Machine Vision to Shape Analysis in Leaf and Plant Identification[J].1993,36(1):163-171.
[50]Guyer D E, Miles G E, Schreiber M M. Machine Vision and Image Processing for Plant Identification[J]. Transactions of the ASAE.1986:1500-1507.
[51]Hu M. Visual pattern recognition by moment invariants[J]. IEEE Trans on Information Theory. 1962,8(2):179-187.
[52]Lee C, Chen S. Classification of leaf images[J]. International Journal of Imaging Systems and Technology.2006,16(1):15-23.
[53]Li Z, An Q, Ji C. CLASSIFICATION OF WEED SPECIES USING ARTIFICIAL NEURAL NETWORKS BASED ON COLOR LEAF TEXTURE FEATURE[M]. Computer and Computing Technologies in Agriculture Ⅱ, Volume 2, Zhao C, Li D, Springer Boston,2009:294,1217.
[54]Liu J, Zhang S, Deng S. A Method of Plant Classification Based on Wavelet Transforms and Support Vector Machines[M]. Emerging Intelligent Computing Technology and Applications, Huang D, Jo K, Lee H, et al, Springer Berlin/Heidelberg,2009:5754,253.
[55]Mcdonald T, Chen Y R. Application of morphological image processing in agriculture[J]. Transactions of the ASAE.1990,33(4):1345-1352.
[56]Nam Y, Hwang E. A Shape-Based Retrieval Scheme for Leaf Images[M]. Advances in Multimedia Information Processing-PCM 2005, Ho Y, Kim H, Springer Berlin/Heidelberg,2005:3767,876.
[57]Nam Y, Hwang E, Kim D. CLOVER:A Mobile Content-Based Leaf Image Retrieval System[M]. Digital Libraries:Implementing Strategies and Sharing Experiences, Fox E, Neuhold E, Premsmit P, et al, Springer Berlin/Heidelberg,2005:3815,139.
[58]Nam Y, Hwang E, Kim D. A similarity-based leaf image retrieval scheme Joining shape and venation features[J].110(2).2008:245-259.
[59]Oide M, Ninomiya S. Matching Shape with Self-Intersection:Application to Leaf Classification[J]. IEEE Trans on Image Processing.2004,13(5):653-661.
[60]Park J, Hwang E, Nam Y. A Venation-Based Leaf Image Classification Scheme[M]. Information Retrieval Technology, Ng H, Leong M, Kan M, et al, Springer Berlin/Heidelberg,2006:4182,416.
[61]Sarkar N, Chaudhuri B B. An efficient differential box-counting approach to compute fractal dimension of image[J]. IEEE Trans. On SMC.1994,24(1):115-120.
[62]Shearer S A, Holmes R G. Plant identification using color color-occurrence matrices[J]. Transactions of the ASAE.1990,33(6):2037-2044.
[63]Timmermans A J M, Hulzebosch A A. Computer vision system for on-line sorting of pot plants using an artificial neural network classifier[J].1996,15(1):41-55.
[64]Tomasi C, Manduchi R. Bilateral filtering for gray and color images:Proceedings of the IEEE International Conference on Computer Vision[Z]. Bombay, India:1998839-846.
[65]Tricot C. Curves and Fractal Dimension[M]. New York:Springer-Verlag,1995.
[66]Yonekawa S, Sakai N, Kitani O. Identification of idealized leaf types using simple dimensionless shape factors by image analysis[J]. Trans of the ASAE.1996,39(4):1525-1533.
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |