欢迎访问作物学报，今天是
作物学报

作物学报 ›› 2012, Vol. 38 ›› Issue (02): 374-379.doi: 10.3724/SP.J.1006.2012.00374

• 研究简报 • 上一篇    

基于图像处理和支持向量机的初烤烟叶颜色特征区域分类

潘治利1,**，祁萌2,**，魏春阳3,**，李锋3，张仕祥3，王建伟3，过伟民3，艾志录1,*   

  1. 1 河南农业大学食品科学技术学院, 河南郑州450002; 2 华北水利水电学院, 河南郑州 450008; 3中国烟草总公司郑州烟草研究院, 河南郑州 450001
  • 收稿日期:2011-06-02 修回日期:2011-10-12 出版日期:2012-02-12 网络出版日期:2011-12-01
  • 基金资助:

    本研究由河南省重点学科青年骨干教师建设项目(豫教高[2008]169号)资助。

Color Region Classification of Flue-cured Tobacco Leaves Based on the Image

PAN Zhi-Li1,**,QI Meng2,**,WEI Chun-Yang3,**,LI Feng3,ZHANG Shi-Xiang3,WANG Jian-Wei3,GUO Wei-Min3,AI Zhi-Lu1,*   

  1. 1 College of Food Science and Technology, Henan Agricultural University, Zhengzhou 450002, China; 2 North China University of Water Conservancy and Electric Power, Zhengzhou 450008, China; 3 Zhengzhou Tobacco Research Institute of China National Tobacco Corporation, Zhengzhou 450001, China
  • Received:2011-06-02 Revised:2011-10-12 Published:2012-02-12 Published online:2011-12-01

PDF

2081

被引次数

13

摘要： 颜色是烤烟烟叶品质的重要外在指标之一, 在生产中, 同类颜色烟叶在不同产地却往往存在着较大的差异。采用区域生长方法对烟叶图像进行分割预处理, 然后提取烟叶的颜色特征, 再运用一种新的机器学习算法—支持向量机分类方法对我国烟叶颜色特征进行区域分类。结果发现在小样本情况下, 采用径向基函数作为支持向量模型的核函数, 并确定了适当的模型参数, 所建立模型对烟叶颜色区域特征的回判识别率达100%, 预测识别率达86.67%。支持向量机对典型产地烟叶颜色的分类识别具有良好的应用性能。

关键词: 烟叶, 支持向量机, 颜色, 分类

Abstract: Leaf color is an important indicator of flue-cured tobacco quality; however, there is a big difference among similar color tobacco leaves from different areas. Color features of tobacco leaves were obtained by using Region Growing Method in the pre-processing, and then made region classification by using Support Vector Machine (SVM). The results showed that in the case of small samples, radial basis function was the kernel function of the SVM, and the appropriate model parameters were determined. The classification accuracies for training set and test set of the SVM model were 100% and 86.67%, showing that SVM has a perfect performance in color region classification of tobacco leaves.

Key words: Tobacco leaf, Support vector machine, Color, Classification

[1]Hang Y(黄勇), Zhou J-H(周冀衡), Yang H-Q(杨虹琦), Liu J-L(刘建利), Wang Y(王勇), Zhou Y-H(周义和), Huang Y(黄琰), He X-L(何小力). Cytological observation of leaf and chl oroplast during the flue-cured tobacco maturation. Acta Agron Sin (作物学报), 2006, 32(11): 1767–1770 (in Chinese with English abstract)
[2]Liu H-B(刘华波), He L-Y(贺立源), Ma W-J(马文杰), Li C-Y(李翠英). Color features of transmittance images applied in the classification of tobacco leaves. Trans CSAE (农业工程学报), 2007, 23(9): 169–171 (in Chinese with English abstract)
[3]Zhang F(张帆), Fang R-M(方如明), Cai J-R(蔡健荣). Image retrieval of standard tobacco leaf database. Transact Chin Soc Agric Machin (农业机械学报), 2001, 32(1): 66–68 (in Chinese with English abstract)
[4]Vapnik V. The Nature of Statistical Learning Theory. New York: Springer-Verlag, 1995. pp 20–60
[5]Deng N-Y(邓乃扬), Tian Y-J(田英杰). Support Vector Machine—a New Method in Data Mining (数据挖掘中的新方法——支持向量机). Beijing: Science Press, 2004. pp 12–28 (in Chinese)
[6]Cristianini N, Shawe-Taylor J eds. Li G-Z(李国正), Wang M(王猛), Zeng H-J(曾华军) trans. An Introduction to Support Vector Machines and Other Kernel-based Learning Methods (支持向量机导论). Beijing: Electronics Industry Press, 2004. pp 80–140 (in Chinese)
[7]Zou X-B(邹小波), Zhao J-W(赵杰文). Distinguishing cultivar apples by electronic nose based on multi-resolution decomposition and support vector machine. Chin J Sci Instrum (仪器仪表学报), 2007, 28(3): 534–538 (in Chinese with English abstract)
[8]Tian Y-W(田有文), Wang L-D(王立地), Jiang S-H(姜淑华). Recognition of maize disease based on image processing and SVM. Chin J Sci Instrum (仪器仪表学报), 2006, 27(3): 2123–2124 (in Chinese with English abstract)
[9]Tian Y-W(田有文). A method of recognizing grape disease based on texture feature and support vector machine. Chin J Sci Instrum (仪器仪表学报), 2005, 26(1): 606–608 (in Chinese with English abstract)
[10]Chen Q-S(陈全胜), Zhao J-W(赵杰文), Cai J-R(蔡健荣), Wang X-Y(王新宇). Study on identification of tea using computer vision based on support vector machine. Chin J Sci Instrum (仪器仪表学报), 2006, 27(12): 1704–1706 (in Chinese with English abstract)
[11]Zheng Y-H(郑一华), Xu L-Z(徐立中), Huang F-Z(黄凤辰). Study of water quality analysis based on support vector classification. Chin J Sci Instrum (仪器仪表学报), 2006, 27(3): 2291–2292 (in Chinese with English abstract)
[12]National Standardization Technical Committee of Tobacco (全国烟草标准化技术委员会).YC/T 291-2009, Ambient Condition of Tobacco Grading Laboratory (烟叶分级实验室环境条件). Beijing: Standards Press of China (in Chinese)
[13]Wang Y-J(王艳娟), Chen X-H(陈晓红), Huang X-X(黄晓欣). Automatic extraction of regions of interest. Sci Tech Eng (科学技术与工程), 2007, 7(12): 2867–2871 (in Chinese with English abstract)
[14]Cai H-C(蔡鸿昌), Cui H-X(崔海信), Song W-T(宋卫堂), Gao L-H(高丽红). Preliminary study on photosynthetic pigment content and color feature of cucumber initial bloom stage. Transact CSAE (农业工程学报), 2006, 22(9): 34–38 (in Chinese with English abstract)
[15]Winsvm software
[EB/OL].
[2010-10]http://www.live-share.com/files/363163/winsvm2.88.rar.html.2009-08.
[16]Zhao J-W(赵杰文), Hu H-P(呼怀平), Zou X-B(邹小波). Application of support vector machine to apple classification with near-infrared spectroscopy. Transact CSAE (农业工程学报), 2007, 23(4): 149–152 (in Chinese with English abstract) .
[17]Yuan Z-M(袁哲明), Tan X-S(谭显胜). Nonlinear screening indexes of drought resistance at rice seedling stage based on support vector machine. Acta Agron Sin (作物学报), 2010, 36(7): 1167–1182 (in Chinese with English abstract)
[18]Li M(李明), Zhang C-L(张长利), Fang J-L(房俊龙). Extraction of leaf area index of wheat based on image processing technique. Trans CSAE (农业工程学报), 2010, 26(1): 205–209 (in Chinese with English abstract)
[19]Li R(李睿), Peng X-D(彭新德), Min J(闵军), Xiao F-H(肖放华). Analysis on the txterior quality of rice by digital image processing. Comp Syst Appl (计算机系统与应用), 2011, 20(4): 194–198 (in Chinese with English abstract)
[1] 翟胜男, 曹新有, 李豪圣, 李吉虎, 李法计, 刘金栋, 夏先春, 吕莹莹, 马瑞峰, 王颖, 耿洪伟, 刘建军. 小麦Pod-A1、Pod-D1和Pod-2D位点等位变异对籽粒过氧化物酶活性的遗传效应分析[J]. 作物学报, 2026, 52(6): 1593-1603.
[2] 蒋雨洲, 王甲, 张宏媛, 冯文豪, 王鹏, 李玉义. 化肥配施有机物料对玉米田土壤细菌和真菌群落结构的影响[J]. 作物学报, 2025, 51(5): 1378-1388.
[3] 夏琦, 郭滢, 王坤美, 王思忆, 巨建业, 彭雅雯, 刘忠松, 夏石头. 甘蓝型油菜种子和种皮中水杨酸含量与原花色素积累的关系研究[J]. 作物学报, 2025, 51(5): 1189-1197.
[4] 罗珍, 杨妮, 尚晓晖, 余心城, 朱婧怡, 杨光, 胡笑涛. 基于Planet Scope卫星及无人机多光谱影像的宝鸡峡灌区种植结构信息提取[J]. 作物学报, 2025, 51(12): 3317-3330.
[5] 巨建业, 杨柳, 陈浩, 康雷, 夏石头, 刘忠松. 单细胞核转录组分析揭示油菜种皮分化过程和种子颜色差异原因[J]. 作物学报, 2025, 51(11): 2860-2874.
[6] 赵荣荣, 丛楠, 赵闯. 基于Landsat 8影像提取豫中地区冬小麦和夏玉米分布信息的最佳时相选择[J]. 作物学报, 2024, 50(3): 721-733.
[7] 梁星伟, 杨文亭, 金雨, 胡莉, 傅小香, 陈先敏, 周顺利, 申思, 梁效贵. 玉米穗轴的颜色变化, 是偶然还是与农艺性状存在关联?——以历年国审普通品种为例[J]. 作物学报, 2024, 50(3): 771-778.
[8] 王硕, 鲍天旸, 刘建刚, 段绍光, 简银巧, 李广存, 金黎平, 徐建飞. 基于RGB颜色空间评价马铃薯块茎绿化程度[J]. 作物学报, 2023, 49(4): 1102-1110.
[9] 赵冬兰, 赵凌霄, 刘洋, 张安, 戴习彬, 周志林, 曹清河. 基于RNA-seq的甘薯芽变株系类胡萝卜素基因代谢差异分析[J]. 作物学报, 2023, 49(12): 3239-3249.
[10] 许乃银, 赵素琴, 张芳, 付小琼, 杨晓妮, 乔银桃, 孙世贤. 基于GYT双标图对西北内陆棉区国审棉花品种的分类评价[J]. 作物学报, 2021, 47(4): 660-671.
[11] 邱红梅, 陈亮, 侯云龙, 王新风, 陈健, 马晓萍, 崔正果, 张玲, 胡金海, 王跃强, 邱丽娟. 大豆种子颜色遗传调控机制研究进展[J]. 作物学报, 2021, 47(12): 2299-2313.
[12] 翟胜男, 郭军, 刘成, 李豪圣, 宋健民, 刘爱峰, 曹新有, 程敦公, 李法计, 何中虎, 夏先春, 刘建军. 小麦类胡萝卜素合成途径关键基因Lcye功能分析[J]. 作物学报, 2020, 46(10): 1485-1495.
[13] 李萍,侯万伟,刘玉皎. 青海高原耐旱蚕豆品种青海13号响应干旱胁迫蛋白质组学分析[J]. 作物学报, 2019, 45(2): 267-275.
[14] 韩仲志, 赵友刚. 利用花生荚果图像特征识别品种与检验种子[J]. 作物学报, 2012, 38(03): 535-540.
[15] 刘金帅, 赖惠成, 贾振红. 基于YCbCr颜色空间和Fisher判别分析的棉花图像分割研究[J]. 作物学报, 2011, 37(07): 1274-1279.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
京ICP备15008789号-2