[1]金沙沙,贾良权,龙伟,等.基于特征选择与骨架提取的种子萌发的芽长、根长检测[J].江苏农业学报,2021,(03):597-605.[doi:doi:10.3969/j.issn.1000-4440.2021.03.007]
　JIN Sha-sha,JIA Liang-quan,LONG Wei,et al.Detection of seed bud length and root length based on feature selection and skeleton extraction[J].,2021,(03):597-605.[doi:doi:10.3969/j.issn.1000-4440.2021.03.007]
点击复制

基于特征选择与骨架提取的种子萌发的芽长、根长检测()
分享到：

江苏农业学报[ISSN:1006-6977/CN:61-1281/TN]

卷:
期数:
2021年03期
页码:
597-605
栏目:
耕作栽培·资源环境
出版日期:
2021-06-30

文章信息/Info

Title:
Detection of seed bud length and root length based on feature selection and skeleton extraction
作者:
金沙沙1; 2; 贾良权1; 2; 龙伟1; 2; 祁亨年1; 2; 赵光武3; 高璐1; 2; 蒋林华1; 2
(1.湖州师范学院信息工程学院，浙江湖州313100；2.浙江省现代农业资源智慧管理与应用研究重点实验室，浙江湖州313100；3.浙江农林大学农业与食品科学学院，浙江杭州311000）
Author(s):
JIN Sha-sha1; 2; JIA Liang-quan1; 2; LONG Wei1; 2; QI Heng-nian1; 2; ZHAO Guang-wu3;  GAO Lu1; 2; JIANG Lin-hua1; 2
(1.School of Information Engineering, Huzhou University, Huzhou 313100, China;2.Zhejiang Provincial Key Laboratory of Smart Management & Application of Modern Agricultural Resources, Huzhou 313100, China;3.College of Agriculture and Food Sciences, Zhejiang A & F University, Hangzhou 311000, China)
关键词:
图像处理; 芽长检测; 根长检测; 颜色特征; 骨架提取
Keywords:
image processing; bud length; root length; color feature; skeleton extraction
分类号:
S339.3+1
DOI:
doi:10.3969/j.issn.1000-4440.2021.03.007
文献标志码:
A
摘要:
芽长是种子活力的一个重要判定标准。传统的芽长检测方法采用人工测量方式，存在费时费力、且受人为主观因素影响较大等问题。利用数字图像处理技术的芽长自动检测算法可以提高芽长测量的效率，并且能够统一测量标准从而避免主观误差。本研究基于特征选择与骨架提取算法原理设计了种子芽长、根长检测复合算法及软件，首先利用颜色特征提取叶片信息，并在整株芽长二值图像中去除叶片区域信息，其次通过圆盘结构元素与线性结构元素腐蚀图像分割出种子图像，获得种子的中心，再对整株芽长二值图像进行图像增强和边缘轮廓处理，最后对芽长图像进行骨架提取与剪枝，依据像素点间的欧氏距离计算芽长与根长。通过对玉米、小麦、水稻的芽长和根长进行测量，结果显示，玉米、小麦与水稻芽长的百分误差分别为2.90%、2.05%、2.40%；根长的百分误差分别为1.90%、2.11%、2.02%。说明基于特征选择与骨架提取检测方法的复合算法能够实现对种子萌发的芽长与根长的高精度、快速检测。
Abstract:
Bud length is an important criterion for seed vigor judgement. Traditional detection methods for bud length used manual measurements, which had the problems such as time consuming and the measuring results were affected by experimenters’ subjective factors greatly. Automatic detection algorithm of bud length using digital image processing technology could improve the detection efficiency and unify the measurement standard to avoid subjective error. A compound algorithm and software for seed bud length and root length detection were designed based on the principle of feature selection and skeleton extraction algorithm. Firstly, the leaf information was extracted based on the color feature, and the leaf region information was wiped off in the binary image of bud length for the whole plant. Secondly, image of the seed was segmented based on eroded images of disk structure element and linear structure element, and the center of the seed was got. Then the binary image for bud length of whole plant was enhancement and the edge contour of the image was processed. After that, skeleton of the bud length image was extracted and the image was pruned, the bud length and root length were calculated according to the Euclidean distance between pixels in the skeleton. Bud length and root length of corn, wheat and rice were measured in the study. The results showed that, average percentage error of the bud length of corn, wheat and rice were 2.90%, 2.05% and 2.40% respectively, while for root length the data were 1.90%, 2.11% and 2.02% respectively. The experimental results show that, the compound algorithm based on feature extraction and skeleton extraction can detect the bud length and root length during seed germination precisely and fastly.

参考文献/References:

[1]MARCOS FILHO J. Seed vigor testing: an overview of the past, present and future perspective[J]. Scientia Agricola, 2015, 72(4): 363-374.
[2]DENG F, QI H N, ZHAO G W. Seed vigor assessment for Cunninghamia lanceolata and Pinus massoniana using image processing[J]. Transactions of the Chinese Society of Agricultural Engineering, 2012, 28(S2): 274-279.
[3]何龙生,俞兵桥,赵光武,等. 根长测定法在常规水稻种子活力测定中的应用[J]. 江苏农业科学, 2019, 47(11): 89-93.
[4]傅丹桂,孙雁,黄正仙,等. 水稻种子不同活力测定方法的比较[J]. 云南农业大学学报(自然科学), 2018, 33(5): 811-817.
[5]何晶,陈敏,陈永刚,等. 基于消食作用优选麦芽适宜芽长[J]. 医药导报, 2018, 37(10): 1178-1181.
[6]IQBAL Z, KHAN M A, SHARIF M, et al. An automated detection and classification of citrus plant diseases using image processing techniques: a review[J]. Computers and Electronics in Agriculture, 2018, 153: 12-32.
[7]BHARGAVA A, BANSAL A. Fruits and vegetables quality evaluation using computer vision: a review[J]. Journal of King Saud University-Computer and Information Sciences, 2018, doi: https://doi.org/10.1016/j.jksuci.2018.06.002.
[8]SREEKANTHA D K, KAVYA A M. Agricultural crop monitoring using IOT-a study[C]//KARPAGAM COLLEGE OF ENGINEERING, IEEE MADRAS SECTION. In proceedings of the 2017 11th international conference on intelligent systems and control (ISCO). Coimbatore, India: IEEE, 2017: 134-139.
[9]HOWARTH M S, STANWOOD P C. Measurement of seedling growth rate by machine vision[J]. Transactions of the ASAE, 1993, 36(3): 959-963.
[10]路文超,罗斌,潘大宇,等. 基于图像处理的小麦穗长和小穗数同步测量[J].中国农机化学报,2016, 37(6): 210-215.
[11]YAMAMOTO K, GUO W, NINOMIYA S. Node detection and internode length estimation of tomato seedlings based on image analysis and machine learning[J]. Sensors, 2016, 16(7): 1044.
[12]张万红.基于图像法的离体小麦叶片几何参数计算[J]. 浙江大学学报(农业与生命科学版), 2018, 44(6): 748-754.
[13]冯青春,陈建,李翠玲,等. 基于光度立体视觉的蔬菜秧苗叶片形态测量方法[J]. 农业机械学报, 2018, 49(5): 43-50.
[14]FLAVEL R J, GUPPY C N, RABBI S M R, et al. An image processing and analysis tool for identifying and analysing complex plant root systems in 3D soil using non-destructive analysis: root1[J]. PloS One, 2017, 12(5): e0176433.
[15]杨红云,路艳,孙爱珍,等. 水稻叶片几何参数无损测量方法研究[J]. 江西农业大学学报, 2020, 42(2): 407-418.
[16]杨丹. Matlab图像处理实例详解[M]. 北京: 清华大学出版社, 2013: 311-317.
[17]杜枭雄. 苹果采摘机器人视觉系统的目标识别研究[D]. 汉中:陕西理工大学, 2019.
[18]张志斌,罗锡文,臧英,等. 基于颜色特征的绿色作物图像分割算法[J].农业工程学报, 2011, 27(7): 183-189.
[19]李洪池,罗建. 西藏色季拉山区龙胆科植物种子微形态特征及其系统分类学意义[J]. 植物科学学报, 2019, 37(6): 699-708.
[20]董松，徐晓辉，宋涛，等. 基于过渡区研究的黄瓜病害识别方法[J].南方农业学报，2019，50(9)：2119-2126.
[21]赵建鹏，杨秀峰，李国洪，等. 基于面向对象的设施蔬菜高分遥感影像提取［J］．江苏农业学报，2019,35(4):911-918.
[22]佘银海，王新彦. 基于双目立体视觉的草坪植株高度测量［J］.江苏农业科学，2020，48（4）：215-221.
[23]王金玲. 保持图像骨架连续的剪枝技术及相关问题研究[D]. 济南: 山东师范大学, 2010.
[24]GONZALEZ R C, WOODS R E. Digital image processing [M]. 3rd Edition.Beijing: Publishing House of Electronics Industry, 2017.
[25]梁琳,何卫平,雷蕾,等. 光照不均图像增强方法综述[J]. 计算机应用研究, 2010, 27(5): 1625-1628.

相似文献/References:

[1]车金庆,王帆,王艺洁,等.基于视觉注意机制的黄绿色苹果图像分割[J].江苏农业学报,2018,(06):1347.[doi:doi:10.3969/j.issn.1000-4440.2018.06.021]
　CHE Jin-qing,WANG Fan,WANG Yi-jie,et al.A segmentation method of yellow and green apple images based on visual attention mechanism[J].,2018,(03):1347.[doi:doi:10.3969/j.issn.1000-4440.2018.06.021]
[2]车金庆,王帆,吕继东,等.重叠苹果果实的分离识别方法[J].江苏农业学报,2019,(02):469.[doi:doi:10.3969/j.issn.1000-4440.2019.02.030]
　CHE Jin-qing,WANG Fan,LYU Ji-dong,et al.Separation and recognition method for overlapped apple fruits[J].,2019,(03):469.[doi:doi:10.3969/j.issn.1000-4440.2019.02.030]

备注/Memo

备注/Memo:
收稿日期：2020-10-25基金项目：国家自然科学基金青年基金项目(31701512)；浙江省重点研发项目（2019C02013、2020C02020）；湖州市公益性应用研究项目（2019GZ15）；浙江省教育厅一般科研项目（Y201941626）作者简介：金沙沙（1994-），女，浙江湖州人，硕士研究生，研究方向为图像处理。(E-mail) 1030273748@qq.com通讯作者：贾良权，(Tel) 0572-2321106；(E-mail) 02426@zjhu.edu.cn。蒋林华，(E-mail) 11594@zjhu.edu.cn
更新日期/Last Update: 2021-07-05