欢迎访问作物学报，今天是
作物学报

作物学报 ›› 2010, Vol. 36 ›› Issue (3): 502-507.doi: 10.3724/SP.J.1006.2010.00502

• 耕作栽培·生理生化 • 上一篇    下一篇

基于颜色阈值的田间籽棉图像分割技术

王玲1，王萍2，陈兵林3，刘善军4，姬长英1,*   

  1. 1南京农业大学工学院，江苏南京210031；2江西农业大学成人教育学院，江西南昌330045；3南京农业大学农业部作物生长调控重点开放实验室，江苏南京210095；4江西农业大学农学院，江西南昌330045
  • 收稿日期:2009-05-31 修回日期:2009-12-08 出版日期:2010-03-12 网络出版日期:2010-01-22
  • 通讯作者: 姬长英,E-mail: chyji@njau.edu.cn; Tel: 13951994628
  • 基金资助:

    本研究由国家高技术研究发展计划（863计划）项目（2006AA10Z259）和2005年江苏省农机项目（GXZ05013）资助。

Image Segmentation Technique of Field Cotton Based on Color Threshold

WANG Ling1,WANG Ping2,CHEN Bing-Lin3,LIU Shan-Jun4,JI Chang-Ying1,*   

  1. 1 College of Engineering, Nanjing Agricultural University, Nanjing 210031, China; 2 College of Adult Education, Jiangxi Agricultural University, Nanchang 330045, China; 3 Key Laboratory of Crop Regulation, Ministry of Agriculture, Nanjing Agricultural University, Nanjing 210095, China;
    4 College of Agronomy, Jiangxi Agricultural University, Nanchang 330045, China
  • Received:2009-05-31 Revised:2009-12-08 Published:2010-03-12 Published online:2010-01-22
  • Contact: JI Chang-Ying,E-mail: chyji@njau.edu.cn; Tel: 13951994628

PDF

1963

被引次数

28

摘要：

为正确分割田间籽棉图像，将棉花与背景视为二个类别，在典型的未成熟籽棉图像和不同质量等级的成熟/过熟籽棉图像中，用肉眼选取20 000个白棉、黄染棉和污染棉等棉花像素以及20 000个棉株、土壤等背景像素，在RGB、HSI、La*b*和Hunter颜色空间下获取二类像素之间的颜色阈值，基于阈值进行图像分割，选取噪声较少的HSI和La*b*颜色空间，进一步基于形态学滤波器去噪，实验结果表明，907幅籽棉图像分割的准确率为87.21%和86.33%。HSI颜色空间更适合分割成熟籽棉图像，La*b*颜色空间则适合未成熟籽棉；颜色阈值覆盖范围广，基于速度的阈值分割法能够适应田间籽棉环境。

关键词: 田间棉花, 图像分割, 颜色阈值, 去噪

Abstract:

The goal of cotton production in China is to improve corresponding rate of cotton quality grade; foreign fibers, adulteration, and cotton baling inconsistent phenomenon to decrease continuously. With the background, machine vision and pattern recognition technologies are introduced into traditional picking task to discriminate maturity degree and grade of quality of field cotton, which will solve the problem of picking cotton by the way from source, so that various cotton varieties can be adapted, pollution caused by agriculture chemicals can be avoided, labor cost can be reduced and agriculture cost can be decreased. In order to segment field cotton images exactly, we regarded cotton and its background as two classes and segmented them based on their color threshold. A total of 20 000 white, yellow, and stain cotton pixels and 20 000 background pixels of soil and cotton plant, including cotton bracteole, leaf, and branch, were extracted from typical under-ripe cotton images and ripe/over-ripe cotton images with various quality grades from 1 to 7. Color threshold of two classes of cotton and its background pixels were obtained in RGB, HSI, La*b*, and Hunter color space respectively; on the basis of which cotton regions were segmented from images; and HSI and La*b* color spaces were selected respectively by using S below 28, I over 108, L over 118, a* from 123 to 134, b* below 136 with less segmentation noise which would be removed based on morphological filter. The experiment results showed that 907 cotton images were segmented with an accuracy of 87.21% and 86.33% in HSI and La*b* color space respectively. The front images were segmented with an accuracy of 90.83% and 89.98% and the side images with an accuracy of 83.33% and 82.42%. Ripe cotton images were segmented perfectly in HSI color space while under-ripe cotton images in La*b* color space, and the speed-based segmentation method with threshold covering a wide area was preferable for field cotton surroundings.

Key words: Field cotton, Image segmentation, Color thershold, Removing noise

[1] Li N(李宁), Liu D-P(刘东波), Zang Y-M(臧英明). Study on the differences of cottons grading standards between China and other countries. J Dalian Light Ind Inst (大连轻工业学院学报), 2001, 20(4): 309-312 (in Chinese)

[2] Cotton Instrument Test Group (棉花仪器化检验(草案)起草小组). Dialectical relationship of cotton quality grade and color feature grade. China Textile Test (中国纤检), 2005, (5): 5-7 (in Chinese)

[3] Kang T-J, Kim S-C. Zhao Q-M(赵其明) trans, Cui R-F(崔瑞芳) proof. Objective evaluation of the trash and color of raw cotton by image processing and neural network. Foreign Textile Tech (国外纺织技术), 2003, (1): 37-42 (in Chinese)

[4] Xu B, Fang C, Watson M D. Investigating new factors in cotton color grading. J Textile Res, 1998, 68: 779-787

[5] Xu B, Su J, Dale D S, Watson M D. Cotton color grading with a neural network. J Textile Res, 2000, 70: 430-436

[6] Xu B, Dale D S, Huang Y, Watson M D. Cotton color classification by fuzzy logic. J Textile Res, 2002, 72: 504-509

[7] Tilocca A, Borzone P, Carosio S, Durante A. Detecting fabric defects with a neural network using two kinds of optical patterns. J Textile Res, 2002, 72: 545-550

[8] Pelletier M G, Barker G L, Baker R V. Image processing for stripper harvested cotton trash content measurement：A progress report. Proc Beltwide Cotton Conf, 1999, pp 1412-1415

[9] Pavani S K, Mehmet S D, Hamed S S, Eric F H. Segmentation and classification of four common cotton contaminants in X-ray micro-tomographic Images. Conference on Machine Vision Applications in Industrial Inspection, 2004. pp 1-13

[10] Liu L-H(刘立海), Wang Y-P(王延平). Preprocessing and feature extracting of cotton classification. J Data Acquisition & Proc (数据采集与处理), 2001, 16(2): 145-149 (in Chinese with English abstract)

[11] Xu H-Q(许鹤群), Huang J(黄健). Analysis on mature of cotton fiber image. J China Textile Univ (中国纺织大学学报), 1992, 18(1): 78-83(in Chinese)

[12] Wang Y(王勇), Ji C-Y(姬长英). Study on discrimination of mature cotton in early field scenes. Acta Agric Jiangxi (江西农业学报), 2006, 18(6): 141-143(in Chinese with English abstract)

[13] Wang Y(王勇), Shen M-X(沈明霞), Ji C-Y(姬长英). Model and analysis of color for different parts of ripe cotton in picking period. Trans Chin Soc Agric Engineer (农业工程学报), 2007, 23(4): 183-185 (in Chinese with English abstract)

[14] Wang Y(王勇), Shen M-X(沈明霞), Ji C-Y(姬长英). Using color data and shape properties for cotton fruit recognition. Trans Chin Soc Agric Machinery (农业机械学报), 2007, 38(11): 77-79 (in Chinese with English abstract)

[15] David A F, Jean P. Computer Vision-A Modern Approach (计算机视觉一种现代方法). Beijing: Publishing House of Electronics Industry, 2004. pp 83-109 (in Chinese)

[16] Lin K-Y(林开颜), Wu J-H(吴军辉), Xu L-H(徐立鸿). A survey on color image segmentation techniques. J Image Grap (中国图像图形学报), 2005, 10(1): 1-10 (in Chinese with English abstract)

[17] Gonzalez R C, Woods R E. Digital Image Processing (数字图像处理) 2nd edn. Beijing: Publishing House of Electronics Industry, 2004. pp 228-240 (in Chinese)

[18] Lin M(林敏), Ye G-R(叶关荣), Zhao T-D(赵田冬). The design of intelligent classification system for cotton color. Instrument Tech Sensor (仪表技术与传感器), 1997, (8): 25-27 (in Chinese with English abstract)
[1] 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