|Table of Contents|

Measurement Method of Soybean Seed Morphological Parameters Based on Watershed and Statistical Moment(PDF)

《大豆科学》[ISSN:1000-9841/CN:23-1227/S]

Issue:
2019年06期
Page:
960-967
Research Field:
Publishing date:

Info

Title:
Measurement Method of Soybean Seed Morphological Parameters Based on Watershed and Statistical Moment
Author(s):
DING Qi1;  XU Wei1;  LI Meng2;  WANG Xiu-cheng2;  LU Wei1;  GAI Jun-yi2;  WANG Ling1;  XING Guang-nan2
(1.College of Engineering / Engineering Laboratory of Modern Facility Agriculture Technology and Equipment, Nanjing Agricultural University, Nanjing 210031, China; 2.Soybean Research Institute , Nanjing Agricultural University, Nanjing 210095, China)
Keywords:
Soybean seed image;  Watershed;  Counting;  Morphometry;  Software development
PACS:
-
DOI:
10.11861/j.issn.1000-9841.2019.06.0960
Abstract:
In order to promote soybean cultivation and breeding, this study designed a software that can count accurately and measure the morphological parameters of soybean seed, such as area, perimeter, length and width. The color image of soybean seed and calibration plate were collected by high-speed photographic apparatus. The image background was removed based on the ‘Otsu’ threshold method to obtain the binary image of soybean seed. Based on the watershed transformation method, the adhesive soybean seeds in the binary map were segmented, and a series of single-seed and multi-seeds soybean connected domains were obtained. The seed count was corrected for a few multi-seeds connected domains, and then soybean seed count was achieved. The sum of white pixels in each connected domain is used to calculate the soybean seed area. The seed perimeter was calculated by using the correction formula based on the freeman chain code algorithm. The second-order statistical moment is used to obtain the main axis direction of the soybean seed and the soybean seed was twisted to the horizontal direction, and then we calculated the seed length and width by the extreme difference between the horizontal and vertical coordinates of the boundary point. The accuracy of the software was verified by three different sizes of soybean seed materials. The results showed that the accuracy of soybean seed count can reach 100%. Compared with manual measurement, the error of average seed length and average seed width of soybean seeds is generally 0.01-0.04 cm, the relative error was 3.8%-9.7%, and the average relative error is 5.6%. The software and the corresponding image acquisition device can effectively meet the accuracy of agricultural scientific research work with low cost and high work efficiency.

References:

［1］荀一, 鲍官军, 杨庆华,等. 粘连玉米籽粒图像的自动分割方法［J］. 农业机械学报, 2010, 41(4): 163-167. (Yun Y, Bao G J, Yang Q H, et al. Automatic segmentation method of adhesive corn grain image［J］. Transactions of the Chinese Society of Agricultural Machinery, 2010, 41(4): 163-167.)［2］韩明,刘教民,孟军英, 等. 结合局部能量与改进的符号距离正则项的图像目标分割算法［J］. 电子与信息学报, 2015, 37(9): 2047-2054．(Han M, Liu J M, Meng J Y, et al. Image object segmentation algorithm combining local energy and improved symbol distance regularization ［J］. Journal of Electronics & Information Technology, 2015, 37(9): 2047-2054.)［3］Lu Y L. Study for automatic grain insect counting system based on image processing［J］. Microcomputer Information, 2008, 23(24): 311-312. ［4］Ciontault F, Guerin D, Guillemin J P, et al. Infield triticum aestivum ear counting using colour-texture image analysis［J］. New Zealand Journal of Crop and Horticultural Science, 2008,36 (2):117-130. ［5］王润涛, 张长利, 房俊龙,等. 基于机器视觉的大豆籽粒精选技术［J］. 农业工程学报, 2011, 27(8): 355-358. (Wang R T, Zhang C L, Fang J L, et al. Soybean grain selection technology based on machine vision［J］. Transactions of the Chinese Society of Agricultural Engineering, 2011, 27(8): 355-358.) ［6］李琼, 姚遥, 杨青春,等. 基于MATLAB图像处理的大豆颗粒检测方法研究［J］. 中国农学通报, 2018, 34(30): 20-25. (Li Q, Yao Y, Yang Q C, et al. Study on the detection method of soybean granules based on MATLAB image processing［J］. Chinese Agricultural Science Bulletin, 2018, 34(30): 20-25.)［7］戴文华,吴翔,裘正军,等. 基于圆心定位的籽粒计数方法研究［J］. 农机化研究, 2015, 37(7): 198-202. (Dai W H, Wu X, Qiu Z J, et al. Study on grain counting method based on center positioning［J］. Journal of Agricultural Mechanization Research, 2015, 37(7): 198-202.)［8］Zhao P, Li Y. Grain counting method based on image processing［C］//2009 International Conference on Information Engineering and Computer Science. Wuhan:Institute of Electrical and Electronics Engineers, 2009: 1-3.［9］孙晓婷,陈江红. 基于形态重构的豆粒分割算法［J］. 福建工程学院报, 2014, 12(1): 70-73. (Sun X T, Chen J H. Bean segmentation algorithm based on morphological reconstruction ［J］. Journal of Fujian University of Technology, 2014, 12(1): 70-73.)［10］贾鹏, 李永奎, 赵萍. 基于Matlab图像处理的谷物颗粒计数方法研究［J］. 农机化研究, 2009, 31(1): 152-153，156. (Jia P, Li Y K, Zhao P. Study on grain particle counting method based on Matlab image processing［J］. Journal of Agricultural Mechanization Research, 2009, 31(1): 152-153,156.)［11］Wang Y C,Chou J J. Automatic segmentation of touching rice kernels with an active contour model［J］. Transactions of the ASAE, 2004, 47(5): 1803-1811.［12］Tian J Z, Tie Z Z, Li Y, et al. Comparison of two algorithms based on mathematical morphology for segmentation of touching strawberry fruits［J］. Transactions of the Chinese Society of Agricultural Engineering, 2007, 23(9):164-168.［13］Jung Y M, Kang S H, Shen J. Multiphase image segmentation via Modica–Mortola phase transition［J］. SIAM Journal on Applied Mathematics, 2007, 67(5): 1213-1232.［14］李恺. 基于数字图像处理的颗粒分析系统［D］. 济南：齐鲁工业大学, 2015. (Li W. Particle analysis system based on digital image processing ［D］. Jinan:Qilu University of Technology,2015.)［15］黄小玉, 李光林, 马驰等. 基于改进判别区域特征融合算法的近色背景绿色桃子识别［J］. 农业工程学报, 2018,34(23):142-148.（Huang X Y, Li G L, Ma C, et al. Green peach recognition in near-color background based on improved discriminant region feature fusion algorithm［J］. Transactions of the Chinese Society of Agricultural Engineering, 2018, 34(23): 142-148.［16］杨蜀秦. 大米外观品质计算机视觉检测的研究［D］. 杨凌：西北农林科技大学,2005. (Yang Y Q. Research on computer visual inspection of rice appearance quality［D］. Yangling:Northwest A & F University, 2005.)［17］Visen N S, Shashidhar N S, Paliwal J.Identification and segmentation of occluding groups of grain kernels in a grain sample image［J］. Journal of the Agricultural Engineering Research, 2001, 79 (2): 159-166.［18］Zhang G. Separation of touching grain kernels in an image by ellipse fitting and morphological transform algorithm［J］. Biosystems Engineering,2005,92(2):135-142.［19］Long Z Q, En C J. Automatic segmentation method of touching corn kernels in digital image based on improved watershed algorithm ［C］//2011 International Conference on New Technology of Agricultural. Beijing:Institute of Electrical and Electronics Engineers, 2011: 34-37.［20］Barbedo J G A. Counting clustered soybean seeds ［C］//2012 International Conference on Computational Science and Its Applications.Taian:Institute of Electrical and Electronics Engineers,2012:142-145.［21］陈静, 朱伟兴, 苏威. 基于机器视觉的种子千粒重测定系统的设计［J］.传感器与微系统, 2008, 27(9): 97-99. (Chen J, Zhu W X, Su W. Design of seeding 1000-grain weight determination system based on machine vision［J］. Sensors and Microsystems, 2008, 27(9): 97-99.)［22］王小鹏,陈璐,吴双. 基于面积约束和自适应梯度修正的分水岭图像分割［J］. 光电子·激光, 2014,25(11): 2219-2226. (Wang X P, Chen L, Wu S. Watershed image segmentation based on area constraint and adaptive gradient correction［J］. Journal of Optoelectronics Laser, 2014, 25(11): 2219-2226.)［23］孙晓婷,陈江红,陈庆周.基于H-Dome重构的大豆图像分割［J］.大豆科学,2013,32(6):821-824. (Sun X T, Chen J H, Chen Q Z. Image segmentation of soybean based on H-Dome reconstruction［J］. Soybean Science,2013,32(6):821-824.) ［24］Shahin M A, Symons S J. Seed sizing from image of non-singulated grain samples［J］. Canadian Biosystems Engineering, 2005, 47(3): 49-55.［25］Vossepoel A M, Smeulders A W M. Vector code probability and metrication error in the representation of straightlines of finite length, Computer Graphics and Image Processing, 1982, 20(4): 347-364.

Memo

Memo:
-
Last Update: 2020-03-27