基于改进C-V模型的棉花叶片目标提取方法
|
摘要
为解决自然条件下棉花叶片因其轮廓几何边缘长势不均匀所导致的叶片目标提取不精准问题,提出一种基于改进C-V模型的棉花病害叶部目标提取方法。在传统C-V模型的基础上,将长度惩罚项和符号距离函数的约束能量项引入能量模型中,以达到对演化曲线长度变化的约束目的,从而完成对整幅图像目标特征的提取。本研究算法先对待分割的图像设置初始曲线,并利用高斯滤波算子对待分割图像进行平滑滤波处理,然后根据图像全局灰度信息和局部二值匹配信息建立能量方程,根据其离散化形式,对水平集函数进行演化,并从中提取演化曲线,最后根据水平集函数演化过程所满足的终止条件,输出图像分割结果。按照不同天气条件和不同背景采集了1 200幅棉花叶片样本图像,对本研究算法进行测试。试验结果表明:本研究算法对于晴天、阴天和雨天图像中目标(棉花叶片)轮廓提取准确率分别达到82.23%、82.73%和84.60%。分割结果表明,本研究算法能够对3种天气条件(晴天、阴天、雨天)与4种复杂背景(白地膜、黑地膜、秸秆、土壤)特征混合的棉花叶片图像目标特征轮廓实现准确提取。
In order to solve the problem that target extraction of cotton leaf is not accurate due to the geometric edge grows unevenly under natural conditions,a method for extracting leaf targets of cotton diseases based on improved C-V model is proposed.The algorithm is improved on the basis of conventional model called C-V.The length penalty term and constrained energy term of symbolic distance function are introduced into the energy model,so as to achieve the goal that the length variation of evolution curve is constrained,thus,the extraction process of the target feature for the whole image is completed.First,an initial curve for the segmented images is set by this algorithm,and the segmented images are processed smoothly by Gauss filter operator.Then,the energy equation is established according to the global gray information of the images and the local two value matching information,and the evolution curve is extracted from the evolved level set function according to the discrete form of energy equation.Finally,according to the end condition of the evolution of the level set function,the segmentation result is output.A total of 1 200 images are gathered according to different weather conditions and different backgrounds,and the segmentation performance of the proposed algorithm is evaluated.Experimental results showed that,for the images taken in sunny day,cloudy day and after raining,the contour extraction accuracies of the algorithm are 82.23%,82.73% and 84.60%respectively.Theexperimental results demonstrate that,for cotton leaf images that 3 weather conditions(sunny,cloudy,rainy)are mixed with 4 complex backgrounds(white mulch film,black mulch film,straw,soil),its target feature contours can be extracted accurately by this algorithm.It can provide support for the extraction and identification of cotton leaf diseases and insect pests,and provide reference for the extraction of leaves from other plants.
In order to solve the problem that target extraction of cotton leaf is not accurate due to the geometric edge grows unevenly under natural conditions,a method for extracting leaf targets of cotton diseases based on improved C-V model is proposed.The algorithm is improved on the basis of conventional model called C-V.The length penalty term and constrained energy term of symbolic distance function are introduced into the energy model,so as to achieve the goal that the length variation of evolution curve is constrained,thus,the extraction process of the target feature for the whole image is completed.First,an initial curve for the segmented images is set by this algorithm,and the segmented images are processed smoothly by Gauss filter operator.Then,the energy equation is established according to the global gray information of the images and the local two value matching information,and the evolution curve is extracted from the evolved level set function according to the discrete form of energy equation.Finally,according to the end condition of the evolution of the level set function,the segmentation result is output.A total of 1 200 images are gathered according to different weather conditions and different backgrounds,and the segmentation performance of the proposed algorithm is evaluated.Experimental results showed that,for the images taken in sunny day,cloudy day and after raining,the contour extraction accuracies of the algorithm are 82.23%,82.73% and 84.60%respectively.Theexperimental results demonstrate that,for cotton leaf images that 3 weather conditions(sunny,cloudy,rainy)are mixed with 4 complex backgrounds(white mulch film,black mulch film,straw,soil),its target feature contours can be extracted accurately by this algorithm.It can provide support for the extraction and identification of cotton leaf diseases and insect pests,and provide reference for the extraction of leaves from other plants.
引文
[1]雷亚平,魏晓文,刘志红.中国棉花产业发展现状及展望[J].农业展望,2014,10(9):43-47Lei Y P,Wei X W,Liu Z H.Present status and outlook of cotton industry development in China[J]. Agricultural Outlook,2014,10(9):43-47(in Chinese)
[2]唐海明,余筱南.我国棉花病虫害综合防治研究的现状及展望[J].作物研究,2004,18(S1):425-429Tang H M,Yu X N.Present status and outlook of integrated pest management of cotton diseases and insect pests in China[J].Crop Research,2004,18(S1):425-429(in Chinese)
[3]张景珍.棉花病虫害综防策略与技术[J].中国棉花,1991,18(5):38-39Zhang J Z. Cotton pest integrated control strategy and technology[J].China Cotton,1991,18(5):38-39(in Chinese)
[4]王文静.机器视觉技术在现代农业中的应用[J].现代农业科技,2014(8):335-335Wang W J.Application of machine vision technique in modern agriculture[J]. ModernAgriculturalScienceand Technology,2014(8):335-335(in Chinese)
[5]刁智华,王会丹,魏伟.机器视觉在农业生产中的应用研究[J].农机化研究,2014,36(3):206-211Diao Z H,Wang H D,Wei W.Summary of research on machine vision application in agricultural production[J].Journal of Agricultural Mechanization Research,2014,36(3):206-211(in Chinese)
[6]王小铭.计算机图像图形学应用研究的现状与发展策略刍议[J].华南师范大学学报:自然科学版,1998,30(4):108-111Wang X M.The current status and development strategy of applied research of computer image and graphics[J].Journal of South China Normal University:Natural Science Edition,1998,30(4):108-111(in Chinese)
[7]苏礼楷,王小铭.基于轮廓特征点检测的植物叶片几何建模[J].华南师范大学学报:自然科学版,2009,41(4):39-42Su L K,Wang X M.Geometrical modeling of leaf shape based on image processing and feature points detection[J].Journal of South China Normal University:Natural Science Edition,2009,41(4):39-42(in Chinese)
[8] Otsu N. A threshold selection method from gray-level histogram[J].IEEE Transactions on Systems Man&Cybernetics,1979,9(1):62-66
[9]赵德升,毛罕平,陈树人,张元.杂草识别中背景分割方法的比较研究[J].农机化研究,2009,31(11):76-79Zhao D S,Mao H P,Chen S R,Zhang Y.Research of different background segmentation algorithms for weed identification[J].Journal of Agricultural Mechanization Research,2009,31(11):76-79(in Chinese)
[10]胡波,毛罕平,张艳诚.基于二维直方图的杂草图像分割算法[J].农业机械学报,2007,38(4):119-202Hu B,Mao H P,Zhang Y C.Weed image segmentation algorithm based on two-dimensional histogram[J].Transactions of the Chinese Society for Agricultural Machinery,2007,38(4):119-202(in Chinese)
[11]张武,黄帅,汪京京,刘连忠.复杂背景下小麦叶部病害图像分割方法研究[J].计算机工程与科学,2015,37(7):1349-1354Zhang W,Huang S,Wang J J,Liu L Z.A segmentation method for wheat leaf images with disease in complex background[J].Computer Engineering and Science,2015,37(7):1349-1354(in Chinese)
[12]张艳诚,毛罕平,胡波,李明喜.作物病害图像中重叠病斑分离算法[J].农业机械学报,2008,39(2):112-115Zhang Y C,Mao H P,Hu B,Li M X.Separate algorithm for overlapping spots in crop disease image[J].Transactions of the Chinese Society for Agricultural Machinery,2008,39(2):112-115(in Chinese)
[13]毛罕平,张艳诚,胡波.基于模糊C均值聚类的作物病害叶片图像分割方法研究[J].农业工程学报,2008,24(9):136-140Mao H P,Zhang Y C,Hu B.Segmentation of crop disease leaf images using fuzzy C-means clustering algorithm[J].Transactions of the Chinese Society of Agricultural Engineering,2008,24(9):136-140(in Chinese)
[14]刁智华,王欢,宋寅卯,王云鹏.基于颜色和形状特征的棉花害螨图像分割方法[J].农机化研究,2013,35(3):50-55Diao Z H, Wang H,Song Y M, Wang Y P.Image segmentation method for cotton mite disease image based on color feature and shape feature[J].Journal of Agricultural Mechanization Research,2013,35(3):50-55(in Chinese)
[15] Osher S,Sethian J A.Fronts propagating with curvaturedependent speed:Algorithms based on Hamilton-Jacobi formulations[J].Journal of Computational Physics,1988,79(1):12-49
[16]王斌,李洁,高新波.一种基于边缘与区域信息的先验水平集图像分割方法[J].计算机学报,2012,35(5):1067-1072Wang B,Li J,Gao X B.An edge-and region-based level set method with shape priors for image segmentation[J].Chinese Journal of Computers,2012,35(5):1067-1072(in Chinese)
[17] Caselles V,Kimmel R,Sapiro G.Geodesic active contours[J].International Journal of Computer Vision,1997,22(1):61-79
[18] Malladi R,Sethian J A,Vemuri B C.Shape modeling with front propagation:A level set approach[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,1995,17(2):158-175
[19] Chan T F,Vese L A.Active contours without edges[J].IEEE Transactions on Image Processing,2001,10(2):266-277
[20] Gomes J,Faugeras O.Reconciling distance functions and level sets[J].Journal of Visual Communication&Image Representation,2000,11(2):209-223
[21] Li C M,Xu C Y,Gui C F,Fox M D.Level set evolution without re-initialization:A new variational formulation[C].In:Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition,2005.Los Alamitos:IEEE Computer Society Press,2005:430-436
[22]崔玉玲.基于改进符号距离函数的变分水平集图像分割算法[J].模式识别与人工智能,2013,26(11):1033-1040Cui Y L. A variational level set method for image segmentation based on improved signed distance function[J].Pattern Recognition and Artificial Intelligence,2013,26(11):1033-1040(in Chinese)
[23]常先堂.基于PDE的变分水平集图像分割方法[D].大连:大连理工大学,2006.Chang X T. PDE-based variational level set image segmentation methods[D].Dalian:Dalian University of Technology,2006(in Chinese)
[24]刘瑞娟,何传江,原野.融合局部和全局图像信息的活动轮廓模型[J].计算机辅助设计与图形学学报,2012,24(3):364-371Liu R J,He C J,Yuan Y.Active contours driven by local land global image fitting energy[J].Journal of ComputerAided Design&Computer Graphics,2012,24(3):364-371(in Chinese)
[25] Li C,Xu C,Gui C,Fox M D.Distance regularized level set evolution and its application to image segmentation[J].IEEE Transactions on Image Processing,2010,19(12):3243-3254
[26] Esodoglu S,Smereka P.A variational formulation for a level set representation of multiphase flow and area preserving curvature flow[J]. Communications in Mathematical Sciences,2007,6(1):125-148
[27] Li C M,Kao C Y,Gore J C,Ding Z H.Minimization of region-scalable fitting energy for image segmentation[J].IEEE Transactions on Image Processing,2008,17(10):1940-1949
[28]戴丽萍,张雪萍,李卓立.基于图割和改进的变分水平集的图像分割方法[J].计算机与数字工程,2012,40(10):130-132Dai L P,Zhang X P,Li Z L.Image segmentation approach based on graph cuts and improved variational level set[J].Computer&Digital Engineering,2012,40(10):130-132(in Chinese)
[29]杨威,李俊山,史德琴,胡双演.基于改进变分水平集的红外图像分割方法[J].计算机工程,2008,34(4):196-197,200Yang W,Li J S,Shi D Q, Hu S Y.Infrared image segmentation based on improved variational level set[J].Computer Engineering,2008,34(4):196-197,200(in Chinese)
[2]唐海明,余筱南.我国棉花病虫害综合防治研究的现状及展望[J].作物研究,2004,18(S1):425-429Tang H M,Yu X N.Present status and outlook of integrated pest management of cotton diseases and insect pests in China[J].Crop Research,2004,18(S1):425-429(in Chinese)
[3]张景珍.棉花病虫害综防策略与技术[J].中国棉花,1991,18(5):38-39Zhang J Z. Cotton pest integrated control strategy and technology[J].China Cotton,1991,18(5):38-39(in Chinese)
[4]王文静.机器视觉技术在现代农业中的应用[J].现代农业科技,2014(8):335-335Wang W J.Application of machine vision technique in modern agriculture[J]. ModernAgriculturalScienceand Technology,2014(8):335-335(in Chinese)
[5]刁智华,王会丹,魏伟.机器视觉在农业生产中的应用研究[J].农机化研究,2014,36(3):206-211Diao Z H,Wang H D,Wei W.Summary of research on machine vision application in agricultural production[J].Journal of Agricultural Mechanization Research,2014,36(3):206-211(in Chinese)
[6]王小铭.计算机图像图形学应用研究的现状与发展策略刍议[J].华南师范大学学报:自然科学版,1998,30(4):108-111Wang X M.The current status and development strategy of applied research of computer image and graphics[J].Journal of South China Normal University:Natural Science Edition,1998,30(4):108-111(in Chinese)
[7]苏礼楷,王小铭.基于轮廓特征点检测的植物叶片几何建模[J].华南师范大学学报:自然科学版,2009,41(4):39-42Su L K,Wang X M.Geometrical modeling of leaf shape based on image processing and feature points detection[J].Journal of South China Normal University:Natural Science Edition,2009,41(4):39-42(in Chinese)
[8] Otsu N. A threshold selection method from gray-level histogram[J].IEEE Transactions on Systems Man&Cybernetics,1979,9(1):62-66
[9]赵德升,毛罕平,陈树人,张元.杂草识别中背景分割方法的比较研究[J].农机化研究,2009,31(11):76-79Zhao D S,Mao H P,Chen S R,Zhang Y.Research of different background segmentation algorithms for weed identification[J].Journal of Agricultural Mechanization Research,2009,31(11):76-79(in Chinese)
[10]胡波,毛罕平,张艳诚.基于二维直方图的杂草图像分割算法[J].农业机械学报,2007,38(4):119-202Hu B,Mao H P,Zhang Y C.Weed image segmentation algorithm based on two-dimensional histogram[J].Transactions of the Chinese Society for Agricultural Machinery,2007,38(4):119-202(in Chinese)
[11]张武,黄帅,汪京京,刘连忠.复杂背景下小麦叶部病害图像分割方法研究[J].计算机工程与科学,2015,37(7):1349-1354Zhang W,Huang S,Wang J J,Liu L Z.A segmentation method for wheat leaf images with disease in complex background[J].Computer Engineering and Science,2015,37(7):1349-1354(in Chinese)
[12]张艳诚,毛罕平,胡波,李明喜.作物病害图像中重叠病斑分离算法[J].农业机械学报,2008,39(2):112-115Zhang Y C,Mao H P,Hu B,Li M X.Separate algorithm for overlapping spots in crop disease image[J].Transactions of the Chinese Society for Agricultural Machinery,2008,39(2):112-115(in Chinese)
[13]毛罕平,张艳诚,胡波.基于模糊C均值聚类的作物病害叶片图像分割方法研究[J].农业工程学报,2008,24(9):136-140Mao H P,Zhang Y C,Hu B.Segmentation of crop disease leaf images using fuzzy C-means clustering algorithm[J].Transactions of the Chinese Society of Agricultural Engineering,2008,24(9):136-140(in Chinese)
[14]刁智华,王欢,宋寅卯,王云鹏.基于颜色和形状特征的棉花害螨图像分割方法[J].农机化研究,2013,35(3):50-55Diao Z H, Wang H,Song Y M, Wang Y P.Image segmentation method for cotton mite disease image based on color feature and shape feature[J].Journal of Agricultural Mechanization Research,2013,35(3):50-55(in Chinese)
[15] Osher S,Sethian J A.Fronts propagating with curvaturedependent speed:Algorithms based on Hamilton-Jacobi formulations[J].Journal of Computational Physics,1988,79(1):12-49
[16]王斌,李洁,高新波.一种基于边缘与区域信息的先验水平集图像分割方法[J].计算机学报,2012,35(5):1067-1072Wang B,Li J,Gao X B.An edge-and region-based level set method with shape priors for image segmentation[J].Chinese Journal of Computers,2012,35(5):1067-1072(in Chinese)
[17] Caselles V,Kimmel R,Sapiro G.Geodesic active contours[J].International Journal of Computer Vision,1997,22(1):61-79
[18] Malladi R,Sethian J A,Vemuri B C.Shape modeling with front propagation:A level set approach[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,1995,17(2):158-175
[19] Chan T F,Vese L A.Active contours without edges[J].IEEE Transactions on Image Processing,2001,10(2):266-277
[20] Gomes J,Faugeras O.Reconciling distance functions and level sets[J].Journal of Visual Communication&Image Representation,2000,11(2):209-223
[21] Li C M,Xu C Y,Gui C F,Fox M D.Level set evolution without re-initialization:A new variational formulation[C].In:Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition,2005.Los Alamitos:IEEE Computer Society Press,2005:430-436
[22]崔玉玲.基于改进符号距离函数的变分水平集图像分割算法[J].模式识别与人工智能,2013,26(11):1033-1040Cui Y L. A variational level set method for image segmentation based on improved signed distance function[J].Pattern Recognition and Artificial Intelligence,2013,26(11):1033-1040(in Chinese)
[23]常先堂.基于PDE的变分水平集图像分割方法[D].大连:大连理工大学,2006.Chang X T. PDE-based variational level set image segmentation methods[D].Dalian:Dalian University of Technology,2006(in Chinese)
[24]刘瑞娟,何传江,原野.融合局部和全局图像信息的活动轮廓模型[J].计算机辅助设计与图形学学报,2012,24(3):364-371Liu R J,He C J,Yuan Y.Active contours driven by local land global image fitting energy[J].Journal of ComputerAided Design&Computer Graphics,2012,24(3):364-371(in Chinese)
[25] Li C,Xu C,Gui C,Fox M D.Distance regularized level set evolution and its application to image segmentation[J].IEEE Transactions on Image Processing,2010,19(12):3243-3254
[26] Esodoglu S,Smereka P.A variational formulation for a level set representation of multiphase flow and area preserving curvature flow[J]. Communications in Mathematical Sciences,2007,6(1):125-148
[27] Li C M,Kao C Y,Gore J C,Ding Z H.Minimization of region-scalable fitting energy for image segmentation[J].IEEE Transactions on Image Processing,2008,17(10):1940-1949
[28]戴丽萍,张雪萍,李卓立.基于图割和改进的变分水平集的图像分割方法[J].计算机与数字工程,2012,40(10):130-132Dai L P,Zhang X P,Li Z L.Image segmentation approach based on graph cuts and improved variational level set[J].Computer&Digital Engineering,2012,40(10):130-132(in Chinese)
[29]杨威,李俊山,史德琴,胡双演.基于改进变分水平集的红外图像分割方法[J].计算机工程,2008,34(4):196-197,200Yang W,Li J S,Shi D Q, Hu S Y.Infrared image segmentation based on improved variational level set[J].Computer Engineering,2008,34(4):196-197,200(in Chinese)