基于图像处理的烟叶叶片结构自动分类方法的研究
|
摘要
目前,在烟叶复烤厂中烟叶叶片结构的分析仍然是采用人工的检测手段。针对这种传统工艺方法进行烟叶叶片结构检测和分类的缺点,介绍了图像处理技术在烟叶叶片结构自动分类系统中的研究与应用。讨论了在分类系统中烟叶图像采集关键硬件的选取和图像数据的传输,而后分析了烟叶图像增强、彩色图像分割、连通区域标记、面积的检测、识别和分类等主要的图像处理算法。提出了一种动态的烟叶叶片面积大小分类的算法——最大方差比算法,它是基于类的分离度思想而提出的。该算法对于不同品质的烟叶图像具有自适应性,且计算准确,速度快,能满足实时性要求。实验结果表明该算法能有效地应用于烟叶叶片结构自动分类系统,并取得了令人比较满意的效果。
Today, analyzing the tobacco leaf structure still depends on manpower in the tobaccoindustry. To overcome the flaw of the conventional method of detecting and classifying thetobacco leaf structure, the study and application of image processing in the tobacco leafstructure automatic classification is introduced. Discuss the selection principle of the keyhardware for the image acquisition, which are used in the tobacco classification system.And the transmission of digital image data is presented. Then the details of some mainimage processing algorithms such as image enhancing, color image segmentation,connected component labeling, area detecting, recognizing and classifying are analyzed.This paper presents a algorithm—the maximum ratio of variance, for classifying thetobacco leaf area dynamically. It based on the concept of the scatter of classification. Thealgorithm is adaptive to various quality tobacco images. The algorithm is precious and theprocessing time is decreased. It also runs in real time. Experimental results show that itworks efficiently and stably with the tobacco leaf structure classifying automaticallysystem. The practical results show that it is feasible and satisfactory.
Today, analyzing the tobacco leaf structure still depends on manpower in the tobaccoindustry. To overcome the flaw of the conventional method of detecting and classifying thetobacco leaf structure, the study and application of image processing in the tobacco leafstructure automatic classification is introduced. Discuss the selection principle of the keyhardware for the image acquisition, which are used in the tobacco classification system.And the transmission of digital image data is presented. Then the details of some mainimage processing algorithms such as image enhancing, color image segmentation,connected component labeling, area detecting, recognizing and classifying are analyzed.This paper presents a algorithm—the maximum ratio of variance, for classifying thetobacco leaf area dynamically. It based on the concept of the scatter of classification. Thealgorithm is adaptive to various quality tobacco images. The algorithm is precious and theprocessing time is decreased. It also runs in real time. Experimental results show that itworks efficiently and stably with the tobacco leaf structure classifying automaticallysystem. The practical results show that it is feasible and satisfactory.
引文
[1] Kenneth.R.Castleman. Digital Image Processing(影印版). 北京:清华大学出版社,2003,4:1-3.
[2] 阮秋琦. 数字图像处理学. 北京:电子工业出版社,2001,7:1-6.
[3] 赵荣椿. 数字图象处理导论. 陕西:西北工业大学出版社,2000,8:3-4.
[4] 杨光正,吴岷,张晓莉. 模式识别. 安徽:中国科技大学出版社,2001,7:1-2.
[5] 边肇祺,张学工,等. 模式识别. 北京:清华大学出版社,2002,10:1-2.
[6] R.O.Duda,P.E.Hart,D.G.Stork. 李宏东,姚天翔,等译. 模式分类. 北京:机械工业出版 社,2003,9:7-10.
[7] J.P.Marques de Sá. 吴逸飞译. 模式识别—原理、方法及应用. 北京:清华大学出版社,2003,5: 16-86.
[8] 夏良正. 数字图像处理(修订版). 江苏:东南大学出版社,2003,8:3-4.
[9] Timothy C.Lethbridge,Robert Laganière. 张红光,温遇华,徐巧丽,等译. 面向对象软件工程. 北京:机械工业出版社,2003,4:9-20.
[10] 郑人杰,殷人昆,陶永雷. 实用软件工程(第二版). 北京:清华大学出版,2001,10: 262-264.
[11] 麻志毅,邵维忠. 面向对象方法基础教程. 北京:高等教育出版社,2004,2:5-12.
[12] 王世同,李强,等. Visual C++6.0 编程基础. 北京:清华大学出版社,2001,1:1-2.
[13] 侯俊杰. 深入浅出 MFC(第 2 版). 武汉:华中科技出版社,2002,8:49-50.
[14] 陈元,邓宗明,张睿哲,等. Visual C++6.0 编程实用技术与案例. 北京:清华大学出版 社,2001,11:1-2.
[15] http://vfm.dalsa.com/support/primers/linescanprimer.asp.
[16] DALSAInc. Trillium Camera User’s Manual. Waterloo On Canada,2002,9:16-47.
[17] 丁新民. 微机原理及其应用(第二版). 北京:高等教育出版社,2004,4:210-217.
[18] 曲欣. 烟叶在线实时光电分拣系统研究. 江苏:南京航空航天大学硕士学位论文,2004,3: 15-18.
[19] Coreco Imaging Inc. Sapera 4.0 CAB User’s Manual. St.Laurent, Quebec, Canada, 2001,7:4-11.
[20] 何斌. Visual C++数字图像处理. 北京:人民邮电出版社,2002,8:12-15.
[21] 刘榴娣,刘明奇,党长民. 实用数字图像处理. 北京:北京理工大学出版社,1998,8: 87-111.
[22] Milan Sonka,Vaclav Hlavac,Roger Boyle. 艾海舟,武勃,等译. 图像处理、分析与机器视觉 (第二版). 北京:人民邮电出版社,2003,9:39-50.
[23] 张成海,张铎. 现代自动识别技术与应用. 北京:清华大学出版社,2003,9:222.
[24] 崔屹. 数字图象处理技术与应用. 北京:电子工业出版社,1997,3:121.
[25] 李春雨. 计算机图形学理论与实践. 北京:北京航空航天大学出版社,2004,2:186-187.
[26] S.H.Park,I.D.Yun and S.U.Lee. Color image segmentation based on 3-D clustering and morphological approach. Pattern Recognition,1998,31(8):1061-1076.
[27] 詹劲峰,戚飞龙,王海龙. 基于人眼视觉特性的彩色图象分割方法. 计算机工程,2001, 27(2):68-69.
[28] S.-H.Leng,S.-H.Wang,W.-H.Lau. Lip Image Segmentation Using Fuzzy Clustering Incorporating an Elliptic Shape Function. IEEE Transactions On Image Processing,2004,13(1):51-62.
[29] Shu-Yen Wan and William E.Higgins. Symmetric region growing. IEEE Trans on Image Processing,2003,12(9):1007-1015.
[30] A. Moghaddamzadeh and N. Bourbakis. A fuzzy region growing approach for segmentation of color image. Pattern Recognition,1997,30(6):867-881.
[31] X.Xie,M.Mirmehdi. RAGS: Region-Aided Geometric Snake. IEEE Transactions On Image Processing,2004,13(5):640-652.
[32] 席砺莼,闫宏伟. 彩色图像的分割技术. 微机发展,2003,13(4):46-48.
[33] Jianping Fan and David. K. Y. Yau. Automatic segmentation by integrating color-edge extraction and seeded region growing. IEEE Trans on Image Processing,2001,10(10):1454-1466.
[34] 贾永红. 数字图像处理. 武汉:武汉大学出版社,2003,9:22-25.
[35] 章毓晋. 图象处理和分析. 北京:清华大学出版社,2004,2:17-19.
[36] Fu Chang,Chun-Jen Chen and Chi-Jen Lu. A linear-time component-labeling algorithm using contour tracing technique. Computer Vision Image Understanding,2004,93(2):206-220.
[37] Y.Shima,T.Murakami,M.Koga,H.Yashiro,etal. A high speed algorithm for propagation-type labeling based on block sorting of runs in binary images. Proc. 10th Internat. Conf. Pattern Recognition,IEEE Computer Society Press,1990:655-658.
[38] 张桂林,陈益新,曹伟烜,等. 基于跑长码的连通区域标记算法. 华中理工大学学报,1994, 22(5):11-14.
[39] K.W.Lau,Q.H.Wu. Online training of support vector classifier. Pattern Recognition,2003, 36(8):1913-1920.
[40] Hung-Ju Huang and Chun-Nan Hsu. Bayesian classification for data from the same unknown class. IEEE Transactions On System,Man,and Cybernetics,2002,32(2):137-145.
[41] Vladimir N.Vapnik.张学工译. 统计学习理论的本质. 北京:清华大学出版社,2000,9: 91-98.
[42] 周文,韩力群,李锐. 计算机图像处理技术在烤烟烟叶形状特征提取中的应用. 烟草科 技,2000(1):12-13.
[43] N.OTSU. A Threshold Selection Method from Gray-Level Histogram. IEEE Transactions On System,Man,and Cybernetics,1979,9(1):62-66.
[2] 阮秋琦. 数字图像处理学. 北京:电子工业出版社,2001,7:1-6.
[3] 赵荣椿. 数字图象处理导论. 陕西:西北工业大学出版社,2000,8:3-4.
[4] 杨光正,吴岷,张晓莉. 模式识别. 安徽:中国科技大学出版社,2001,7:1-2.
[5] 边肇祺,张学工,等. 模式识别. 北京:清华大学出版社,2002,10:1-2.
[6] R.O.Duda,P.E.Hart,D.G.Stork. 李宏东,姚天翔,等译. 模式分类. 北京:机械工业出版 社,2003,9:7-10.
[7] J.P.Marques de Sá. 吴逸飞译. 模式识别—原理、方法及应用. 北京:清华大学出版社,2003,5: 16-86.
[8] 夏良正. 数字图像处理(修订版). 江苏:东南大学出版社,2003,8:3-4.
[9] Timothy C.Lethbridge,Robert Laganière. 张红光,温遇华,徐巧丽,等译. 面向对象软件工程. 北京:机械工业出版社,2003,4:9-20.
[10] 郑人杰,殷人昆,陶永雷. 实用软件工程(第二版). 北京:清华大学出版,2001,10: 262-264.
[11] 麻志毅,邵维忠. 面向对象方法基础教程. 北京:高等教育出版社,2004,2:5-12.
[12] 王世同,李强,等. Visual C++6.0 编程基础. 北京:清华大学出版社,2001,1:1-2.
[13] 侯俊杰. 深入浅出 MFC(第 2 版). 武汉:华中科技出版社,2002,8:49-50.
[14] 陈元,邓宗明,张睿哲,等. Visual C++6.0 编程实用技术与案例. 北京:清华大学出版 社,2001,11:1-2.
[15] http://vfm.dalsa.com/support/primers/linescanprimer.asp.
[16] DALSAInc. Trillium Camera User’s Manual. Waterloo On Canada,2002,9:16-47.
[17] 丁新民. 微机原理及其应用(第二版). 北京:高等教育出版社,2004,4:210-217.
[18] 曲欣. 烟叶在线实时光电分拣系统研究. 江苏:南京航空航天大学硕士学位论文,2004,3: 15-18.
[19] Coreco Imaging Inc. Sapera 4.0 CAB User’s Manual. St.Laurent, Quebec, Canada, 2001,7:4-11.
[20] 何斌. Visual C++数字图像处理. 北京:人民邮电出版社,2002,8:12-15.
[21] 刘榴娣,刘明奇,党长民. 实用数字图像处理. 北京:北京理工大学出版社,1998,8: 87-111.
[22] Milan Sonka,Vaclav Hlavac,Roger Boyle. 艾海舟,武勃,等译. 图像处理、分析与机器视觉 (第二版). 北京:人民邮电出版社,2003,9:39-50.
[23] 张成海,张铎. 现代自动识别技术与应用. 北京:清华大学出版社,2003,9:222.
[24] 崔屹. 数字图象处理技术与应用. 北京:电子工业出版社,1997,3:121.
[25] 李春雨. 计算机图形学理论与实践. 北京:北京航空航天大学出版社,2004,2:186-187.
[26] S.H.Park,I.D.Yun and S.U.Lee. Color image segmentation based on 3-D clustering and morphological approach. Pattern Recognition,1998,31(8):1061-1076.
[27] 詹劲峰,戚飞龙,王海龙. 基于人眼视觉特性的彩色图象分割方法. 计算机工程,2001, 27(2):68-69.
[28] S.-H.Leng,S.-H.Wang,W.-H.Lau. Lip Image Segmentation Using Fuzzy Clustering Incorporating an Elliptic Shape Function. IEEE Transactions On Image Processing,2004,13(1):51-62.
[29] Shu-Yen Wan and William E.Higgins. Symmetric region growing. IEEE Trans on Image Processing,2003,12(9):1007-1015.
[30] A. Moghaddamzadeh and N. Bourbakis. A fuzzy region growing approach for segmentation of color image. Pattern Recognition,1997,30(6):867-881.
[31] X.Xie,M.Mirmehdi. RAGS: Region-Aided Geometric Snake. IEEE Transactions On Image Processing,2004,13(5):640-652.
[32] 席砺莼,闫宏伟. 彩色图像的分割技术. 微机发展,2003,13(4):46-48.
[33] Jianping Fan and David. K. Y. Yau. Automatic segmentation by integrating color-edge extraction and seeded region growing. IEEE Trans on Image Processing,2001,10(10):1454-1466.
[34] 贾永红. 数字图像处理. 武汉:武汉大学出版社,2003,9:22-25.
[35] 章毓晋. 图象处理和分析. 北京:清华大学出版社,2004,2:17-19.
[36] Fu Chang,Chun-Jen Chen and Chi-Jen Lu. A linear-time component-labeling algorithm using contour tracing technique. Computer Vision Image Understanding,2004,93(2):206-220.
[37] Y.Shima,T.Murakami,M.Koga,H.Yashiro,etal. A high speed algorithm for propagation-type labeling based on block sorting of runs in binary images. Proc. 10th Internat. Conf. Pattern Recognition,IEEE Computer Society Press,1990:655-658.
[38] 张桂林,陈益新,曹伟烜,等. 基于跑长码的连通区域标记算法. 华中理工大学学报,1994, 22(5):11-14.
[39] K.W.Lau,Q.H.Wu. Online training of support vector classifier. Pattern Recognition,2003, 36(8):1913-1920.
[40] Hung-Ju Huang and Chun-Nan Hsu. Bayesian classification for data from the same unknown class. IEEE Transactions On System,Man,and Cybernetics,2002,32(2):137-145.
[41] Vladimir N.Vapnik.张学工译. 统计学习理论的本质. 北京:清华大学出版社,2000,9: 91-98.
[42] 周文,韩力群,李锐. 计算机图像处理技术在烤烟烟叶形状特征提取中的应用. 烟草科 技,2000(1):12-13.
[43] N.OTSU. A Threshold Selection Method from Gray-Level Histogram. IEEE Transactions On System,Man,and Cybernetics,1979,9(1):62-66.