棉田复杂背景下棉花叶片分割方法

doi:10.6048/j.issn.1001-4330.2018.12.016

新疆农业科学 ›› 2018, Vol. 55 ›› Issue (12): 2288-2295.DOI: 10.6048/j.issn.1001-4330.2018.12.016

棉田复杂背景下棉花叶片分割方法

高攀¹,钱宇珊¹,王佩玲²,吕新²

1.石河子大学信息科学与技术学院,新疆石河子 832000;
2.石河子大学农学院,新疆石河子 832000

收稿日期:2018-09-30 发布日期:2019-04-18
通信作者: 王佩玲,副教授,研究方向为棉花病虫害
作者简介:高攀(1981-),男,安徽灵璧人,副教授,研究方向为智能信息处理和农业信息技术,(E-mail)gp_inf@shzu.edu.cn
基金资助:
国家863计划项目(2013AA100307);兵团高等学校优秀青年项目(CZ027206);石河子大学重大科技攻关项目(GXJS2015-ZDGG08)

The Method of Cotton Leaf Segmentation under the Complex Background in Cotton Fields

GAO Pan¹, QIAN Yu-shan¹, WANG Pei-ling ², L Xin²

1.College of Information Science and Technology, Shihezi University, Shihezi Xinjiang 832000, China; 2. Key Laboratory of Oasis Eco-agriculture of Xinjiang Production and Construction Corps, Shihezi University, Shihezi Xinjiang 832000, China

Received:2018-09-30 Published:2019-04-18
Correspondence author: WANG Pei-ling, female,associate professor
Supported by:
The National 863 Project （2013AA100307）, Excellent Youth Project in Colleges and Universities of XPCC （CZ027206）and Major Science and Technology Key Project （GXJS2015-ZDGG08）

摘要/Abstract

摘要： 【目的】解决棉田复杂背景下棉花叶部病害快速识别问题,为提出一种快速提取棉花植株和分割棉花叶片的方法。【方法】通过棉花植株的RGB颜色特征将植株与土壤进行分离,结合形态学处理技术和彩色分割方法,将植株的茎秆去除,保留棉花叶片部分;分别使用广度搜索分割算法、分水岭分割算法和轮廓搜索分割算法,对棉花叶片图像进行分割提取。【结果】基于广度搜索的分割算法将叶片轮廓搜索出来与原图融合分离出叶片,该算法对于图像结构简单的情况分割效果较好,通过对应的drawContours函数将每个轮廓画出,再与原图定位,将叶片的完整信息也轮廓结合,实现叶片的分离。【结论】基于距离变换的分水岭分割算法存在过分割问题,基于广度搜索分割算法与边缘检测结合对于叶片结构清楚图像分割效果显著,与轮廓搜索算法相比,后者的适用性更广,提取的轮廓层次结构也清楚,分割效果最佳。

关键词: 图像分割; 广度搜索; 分水岭算法; 边缘检测; 轮廓提取

Abstract: 【Objective】 In order to solve the problem of rapid identification of cotton leaf diseases under complex background in cotton field, it is very important to extract cotton plants and segment cotton leaves. Therefore, this paper proposes a fast method of extracting cotton plants and segmenting cotton leaves. 【Method】Firstly, the cotton plant was separated from soil by RGB color feature of cotton plant, and then the stem of cotton plant was removed by combining morphological processing technology and color segmentation method. Then, the cotton leaf image was segmented and extracted by breadth search segmentation algorithm, watershed segmentation algorithm and contour search segmentation algorithm, respectively. 【Result】【Conclusion】The results showed that the watershed segmentation algorithm based on distance transformation had the problem of over-segmentation. The combination of breadth-first search and edge detection had a significant effect on image segmentation with clear blade structure, but compared with contour search algorithm, the latter had a wider applicability, clear contour hierarchy structure and the best segmentation effect.

Key words: image segmentation; breadth search; watershed algorithm; edge detection; contour extraction

中图分类号:

S562

高攀, 钱宇珊, 王佩玲, 吕新. 棉田复杂背景下棉花叶片分割方法[J]. 新疆农业科学, 2018, 55(12): 2288-2295.

GAO Pan, QIAN Yu-shan, WANG Pei-ling , L Xin. The Method of Cotton Leaf Segmentation under the Complex Background in Cotton Fields[J]. Xinjiang Agricultural Sciences, 2018, 55(12): 2288-2295.

参考文献

[1] Murakami S., Homma K., Koike T. Detection of small pests on vegetable leaves usingm GLCM[C]. 2005 ASAE Annual International Meeting, Tampa Florida, USA, 2011.9.
[2] Shariff A.R.M., Aik Y.Y., Hong W.T., et al. Automated identification and counting of pests in the paddy fields using image analysis[C]. Proc. of the 4th World Congress on Computers in Agriculture, Orlando, Florida, USA.2012. 759-764.
[3] 翟治芬,徐哲,周新群,等.基于朴素贝叶斯分类器的棉花盲椿象危害等级识别[J].农业工程学报,2015,31(1):204-211.
ZHAI Zhi-feng, XU Zhe, ZHOU Xin-qun, et al. (2015). Recognition of hazard grade for cotton blind stinkbug based on naive Bayesian classifier [J]. Transactions of the Chinese Society of Agricultural Engineering, 31(1): 204-211.(in Chinese)
[4] 刘立,曾花.基于YIQ颜色空间的火焰轮廓提取算法[J].南华大学学报(自然科学版),2016,30(2):72-77, 82.
LIU Li, ZENG Hua. (2016). Flame contour extraction algorithm based on YIQ color space [J]. Journal of Nanhua University (Natural Science Ed.) , 30(2): 72-77, 82. (in Chinese)
[5] 沈夏炯,吴晓洋,韩道军.分水岭分割算法研究综述[J].计算机工程,2015,41(10):26-30.
SHEN Xia-jiong,WU Xiao-yang HAN Dao-jun. (2015). Summary of watershed segmentation algorithms [J]. Computer Engineering, 41 (10): 26-30. (in Chinese)
[6] 王国权,周小红,蔚立磊.基于分水岭算法的图像分割方法研究[J].计算机仿真,2009,26(5):255-258.
WANG Guo-quan, ZHOU Xiao-hong, WEI Li-lei. (2009). Image segmentation method based on watershed algorithm [J]. Computer Simulation, 26(5): 255-258. (in Chinese)
[7] 刁智华,赵春江,郭新宇,等.分水岭算法的改进方法研究[J].计算机工程,2010,36(17):4-6.
DIAO Zhi-hua, ZHAO Chun-jiang, GUO Xin-yu, et al. (2010). Improvement of watershed algorithm [J]. Computer Engineering, 36(17): 4-6. (in Chinese)
[8] 张效娟,刘技,王昊,等.Snake与多尺度分析的医学图像分割研究[J].计算机工程与应用,2011,47(18):207-209.
ZHANG Xiao-juan, LIU Ji, WANG Hao, et al. (2011). Snake and multiscale analysis for medical image segmentation [J]. Computer Engineering and Applications, 47(18): 207-209. (in Chinese)
[9] 杨康叶,邬春学.基于RGB模型颜色相似性的彩色图像分割[J].计算机系统应用,2013,22(3):128-131, 160.
YANG Kang-ye, WU Chun-xue. (2013). Color image segmentation based on RGB model color similarity [J]. Computer Systems & Applications, 22(3): 128-131, 160. (in Chinese)
[10] 苗姣姣,徐望明.HSV空间和形态学处理相结合的车牌定位方法[J].电视技术,2015,39(5):146-149.
MIAO Jiao-jiao, XU Wang-ming. (2015). License Plate Location Method Based on HSV Spatial and Morphological Processing [J]. Television Technology, 39(5): 146-149. (in Chinese)
[11] 张庭亮,甄倩倩.基于超绿特征与形态学的植保无人机图像农作物分割[J].科技创新与应用,2017,(26):20-22.
ZHANG Ting-liang, ZHEN Qian-qian. (2017). Crop segmentation based on ultra-green feature and morphology for plant protection UAV image [J]. Technology Innovation and Application, (26): 20-22. (in Chinese)
[12] 吴一全,孟天亮,吴诗婳.图像阈值分割方法研究进展20年(1994-2014)[J].数据采集与处理,2015,30(1):1-23.
WU Yi-quang, MENG Tian-liang, WU Shi-hua. (2015). Research progress of image threshold segmentation methods for 20 years (1994-2014) [J]. Journal of Data Acquisition & Processing, 30(1): 1-23. (in Chinese)

棉田复杂背景下棉花叶片分割方法

The Method of Cotton Leaf Segmentation under the Complex Background in Cotton Fields

PDF下载

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 1

编辑推荐

Metrics