欢迎访问作物学报，今天是
作物学报

作物学报 ›› 2012, Vol. 38 ›› Issue (03): 535-540.doi: 10.3724/SP.J.1006.2012.00535

• 耕作栽培·生理生化 • 上一篇    下一篇

利用花生荚果图像特征识别品种与检验种子

韩仲志，赵友刚*   

  1. 青岛农业大学理学与信息科学学院，山东青岛 266109
  • 收稿日期:2011-05-30 修回日期:2011-10-13 出版日期:2012-03-12 网络出版日期:2012-01-04
  • 通讯作者: 赵友刚, E-mail: zhaoyougang@qau.edu.cn, Tel: 0532-86080444
  • 基金资助:

    本研究由国家农业科技成果转化资金项目(2010GB2C600255)，山东省自然科学基金(ZR2009DQ019, ZR2010CM039)，山东省科技攻关项目(2009GG10009057)和青岛市科技发展计划项目(11-2-3-20-nsh)资助。

Variety Identification and Seed Test  by Peanut Pod Image Characteristics

HAN Zhong-Zhi,ZAO You-Gang*   

  1. College of Information Science & Engineering, Qingdao Agricultural University, Qingdao 266109, China
  • Received:2011-05-30 Revised:2011-10-13 Published:2012-03-12 Published online:2012-01-04
  • Contact: 赵友刚, E-mail: zhaoyougang@qau.edu.cn, Tel: 0532-86080444

PDF

1109

被引次数

7

摘要： 为了验证以花生荚果图像特征识别品种和检验种子的可行性，选用代表北方大花生主推区的20份花生品种，从扫描图像获得花生荚果形态、颜色及纹理等50个特征，综合运用主分量分析(PCA)、神经网络(ANN)、支持向量机(SVM)、聚类分析等手段，讨论了品种识别、产地识别、DUS性状的选取和品种聚类过程，研究发现，经PCA优化特征的SVM识别模型识别效果好且识别结果稳定，20个品种的品种识别率达到90%以上。模型对3个不同产地的花生荚果正确识别率达到100%。另外从中筛选出一批对品种特异性、一致性和稳定性(DUS)测试有意义的备选特征，并建立了花生品种的谱系聚类树。研究结果对DUS性状的优选、花生品种及产地的识别及对花生谱系研究有一定参考价值。

关键词: 花生品种识别, 主分量分析, 人工神经网络, 支持向量机, K-均值聚类, DUS测试

Abstract: To verify the feasibility of peanut variety recognition and seed testing by pod image characteristics, we screened 20 peanut varieties mainly released in North peanut regions and collected 50 traits based on pod morphology, colour and texture. We used PCA data optimization, neural networks, support vector machine, and clustering analysis to discuss the vvarieties iidentification, origin recognition, DUS characters selecting method and vvarietiesclustering process. It has been discovered that the PCA optimization SVM model is better and its identification effect is stable. By this model, the variety recognition rate was above 90% for 20 vvarieties, and the correct origin recognition rate of three origins reached 100%. Additionally, we sorted out some useful traits for seeds DUS test from the 50 features and established the dendrogram of 20 peanut varieties. The results of this study provided some references valuable to the selection of DUS traits, peanuts varieties, origin recognition, and peanut pedigree research.

Key words: Peanuts variety recognition, Principal component analysis, Artificial neural network, Support vector machine, K-means clustering, DUS test

[1]Agriculture Department of China, New Varieties of Plants Test Sub-centre (Guangzhou)(农业部植物新品种测试(广州)分中心), Photos Standards of New Peanut Varieties DUS Test (花生新品种DUS测试性状照片拍摄规范). Beijing: China Agriculture Press, 2010 (in Chinese)

[2]UPOV. General Introduction to the Examination of Distinctness, Uniformity and Stability and the Development of Harmonized Descriptions of New Varieties of Plants (TG/1/3). Geneva (Switzerland): The International Union for the Protection of New Varieties of Plants, 2002. p 11

[3]Zhao C-M(赵春明), Han Z-Z(韩仲志), Yang J-Z(杨锦忠), Li N-N(李娜娜), Liang G-M(梁改梅). Study on application of image process in ear traits for DUS testing in maize. Sci Agric Sin (中国农业科学), 2009, 42(11): 4100–4105 (in Chinese with English abstract)

[4]Han Z-Z(韩仲志), Zhao Y-G(赵友刚), Yang J-Z(杨锦忠). Detection of embryo using independent components for kernel RGB images in maize. Trans CSAE (农业工程学报), 2010, 26(3): 222–226 (in Chinese with English abstract)

[5]Han Z-Z(韩仲志), Zhao Y-G(赵友刚). Quality grade detection in peanut using computer vision. Sci Agric Sin (中国农业科学), 2010, 43(18): 3882–3891 (in Chinese with English abstract)

[6]Han Z-Z(韩仲志), Zhao Y-G(赵友刚). A cultivar identification and quality detection method of peanut based on appearance characteristics. J Chin Cereals Oils Assoc (中国粮油学报), 2009, 24(5): 123–126 (in Chinese with English abstract)

[7]Han Z-Z(韩仲志), Zhao Y-G(赵友刚). Image analysis and system simulation on quality and variety of peanut. J Chin Cereals Oils Assoc (中国粮油学报), 2010, 25(11): 114–118 (in Chinese with English abstract)

[8]Sakai N, Yonekawa S, Matsuzaki A. Two-dimensional image analysis of the shape of rice and its application to separating varieties. J Food Eng, 1996, 27: 397–407

[9]Dubey B P, Bhagwat S G, Shouche S P, Sainis J K. Potential of artificial neural networks in varietal identification using morphometry of wheat grains. Biosyst Eng, 2006, 95(1): 61–67

[10]Su Q(苏谦), Wu W-J(邬文锦), Wang H-W(王红武), Wang K(王库), An D(安冬). Fast discrimination of varieties of corn based on near infrared spectra and biomimetic pattern recognition. Spectroscopy Spectral Anal (光谱学与光谱分析), 2009, 29(9): 2413–2416 (in Chinese with English abstract)

[11]Wang F(王方), Wang W(王伟), Zhang C-Y(张春娅), Yin J-T(尹吉泰), Wang S-S(王树生), Lu F-P(路福平). Recognition of production regions for Cabernet Sauvignon dry red wines. Sino-Overseas Grapevine Wine (中外葡萄与葡萄酒), 2008, (1): 4–7 (in Chinese with English abstract)

[12]Hao J-P(郝建平), Yang J-Z(杨锦忠), Du T-Q(杜天庆), Cui F-Z(崔福柱), Sang X-P(桑素平). A study on basic morphologic information and classification of maize cultivars based on seed image process. Acta Agron Sin (中国农业科学), 2008, 41(4): 994–1002. (in Chinese with English abstract)

[13]Yang J-Z(杨锦忠), Hao J-P(郝建平), DuT-Q(杜天庆), Cui F-Z(崔福柱), Sang X-P(桑素平). Discrimination of numerous maize cultivars based on seed image process. Acta Agron Sin (作物学报), 2008, 34(6): 1069−1073 (in Chinese with English abstract)

[14]Lindsay I Smith. A tutorial on Principal Components Analysis [EB/OL]. http://www.cs.otago.ac.nz/cosc453/ student_tutorials/principal_components. pdf, February 26, 2002

[15]Gardnera M W, Dorlinga S R. Artificial neural networks (the multilayer perceptron)—a review of applications in the atmospheric sciences. Atmospheric Environ, 1998, 32: 2627−2636

[16]Hsu C W, Chang C C, Lin C J. A practical guide to support vector classi_cation [EB/OL]. http://www.csie.ntu.edu.tw/~cjlin, April 15, 2010

[17]Likas A, Vlassisb N, Verbeekb J J. The global k-means clustering algorithm. Pattern Recogn, 2003, 36: 451−461

[18]Yang J-Z(杨锦忠), Zhang H-S(张洪生), Hao J-P(郝建平), Du T-Q(杜天庆), Cui F-Z(崔福柱), Li N-N(李娜娜), Liang G-M(梁改梅). Identifying maize cultivars by single characteristics of ears using image analysis. Trans CSAE (农业工程学报), 2011, 27(1): 196−200 (in Chinese with English abstract)

[19]Yang J-Z(杨锦忠), Zhang H-S(张洪生), Zhao Y-M(赵延明), Song X-Y(宋希云), Wang X-Q(王新勤). Quantitative study on the relationships between grain yield and ear 3-D geometry in maize. Sci Agric Sin (中国农业科学), 2010, 43(21): 4367−4374 (in Chinese with English abstract)

[20]GB/T 1532-2008. National Standards of the People's Republic of China: Peanut (中华人民共和国国家标准: 花生). Beijing: Standards Press of China, 2008 (in Chinese)

[21]DB 34 T 252.4-2003. National Standards of the People's Republic of China: Pollution-free peanut IV: Peanut (Kernel)(中华人民共和国国家标准：无公害花生第4部分：花生果/仁). Beijing: Standards Press of China, 2003 (in Chinese)
[1] 唐浩,刘洪,余汉勇,张浙峰,肖应辉,杨益善,陈立云. 基于DUS测试的标准品种形态性状稳定性和重要性分析[J]. 作物学报, 2013, 39(04): 632-641.
[2] 潘治利, 祁萌, 魏春阳, 李锋, 张仕祥, 王建伟, 过伟民, 艾志录. 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[J]. 作物学报, 2012, 38(02): 374-379.
[3] 束永俊, 吴磊, 王丹, 郭长虹. 人工神经网络在作物基因组选择中的应用[J]. 作物学报, 2011, 37(12): 2179-2186.
[4] 王立新,常利芳,李宏博,季伟,刘丽华,赵昌平. 小麦区试品系DUS测试的分子标记[J]. 作物学报, 2010, 36(07): 1114-1125.
[5] 袁哲明*,谭显胜. 基于支持向量机非线性筛选水稻苗期抗旱性指标[J]. 作物学报, 2010, 36(07): 1176-1182.
[6] 黄英姿;毛盛贤. 基因型与环境互作研究的新进展[J]. 作物学报, 1992, 18(02): 116-125.
Viewed
Full text


Abstract

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