[1]杜世伟,李毅念,姚敏,等.基于小麦穗部小穗图像分割的籽粒计数方法[J].南京农业大学学报,2018,41(4):742-751.[doi:10.7685/jnau.201709043]
 DU Shiwei,LI Yinian,YAO Min,et al.Counting method of grain number based on wheatear spikelet image segmentation[J].Journal of Nanjing Agricultural University,2018,41(4):742-751.[doi:10.7685/jnau.201709043]
点击复制

基于小麦穗部小穗图像分割的籽粒计数方法()
分享到:

《南京农业大学学报》[ISSN:1000-2030/CN:32-1148/S]

卷:
41卷
期数:
2018年4期
页码:
742-751
栏目:
出版日期:
2018-07-09

文章信息/Info

Title:
Counting method of grain number based on wheatear spikelet image segmentation
作者:
杜世伟 李毅念 姚敏 李玲 丁启朔 何瑞银
南京农业大学工学院, 江苏 南京 210031
Author(s):
DU Shiwei LI Yinian YAO Min LI Ling DING Qishuo HE Ruiyin
College of Engineering, Nanjing Agricultural University, Nanjing 210031, China
关键词:
小麦穗小穗数籽粒数图像处理抛物线分割
Keywords:
wheatearspikelet numbergrain numberimage processingparabolic segmentation
分类号:
TP391.4
DOI:
10.7685/jnau.201709043
摘要:
[目的]小麦穗部小穗数及籽粒数能够直接反映小麦产量,也是小麦穗表型研究中2个非常重要的参数。[方法]为了快速测量这2个参数,针对小麦穗部正视图像,提出了一种基于图像处理技术的小麦小穗抛物线分割方法,并实现了小穗数及籽粒数的同步识别计数。首先采用图像预处理算法获得麦穗二值图像,然后将二值图像沿穗轴方向的像素按行求和,根据行像素求和曲线图中波峰波谷确定所需要的小穗3个位置点,由小穗3个位置点在二值图像上确定三点拟合抛物线,最后运用抛物线位置分割出各小穗,同时通过阈值法确定各小穗面积值与其籽粒数之间的关系。[结果]使用3个品种小麦穗图像对小穗数及籽粒数识别方法进行验证,结果表明:采用该方法3个品种小麦穗部小穗数识别的平均零误差率为68.16%,平均绝对误差为0.46,平均相对误差为2.99%,对比已有文献识别小穗数方法,识别精度显著提高;3个品种小麦穗部籽粒数识别的平均绝对误差为2.11,平均相对误差为5.62%;3个品种单株麦穗平均测量时间为7.99 s。[结论]运用本方法可以快速高精度地对小麦穗部小穗数及籽粒数进行自动计数。
Abstract:
[Objectives]Wheatear spikelet number and grain number directly reflect the yield of wheat,which are two very important parameters in the research of wheat phenotype. This measuring accuracy about the number of spikelet is very low at present,which can not meet the actual needs of breeding and estimating yield. The literature on measuring grain number has not yet appeared.[Methods]In order to measure these two parameters quickly,a parabolic segmentation method based on image processing technique for wheatear spikelet was presented in this paper,and the synchronously counting spikelet number and grain number were realized by using the wheatear front view image. Firstly,image preprocessing algorithm was used in order to obtain adjusted binary image of wheatear. Then the pixels were summed according to rows of binary image,and the curve of the row pixels sum was plotted. Then the smoothing curve was obtained by using smoothing filtering algorithm and the peaks and troughs of the smoothing curve were obtained by using extracting extremum. The stalk of the wheat was separated by setting a pixels threshold depending on the width difference between the stalk and the ear head. The number of peaks at the ear head in the smoothing curve indicated the number of spikelet. Then the abscissa values of the peaks and troughs were obtained,which represented the ordinal number Y of rows in binary image. A set of intersection points between the rows ordinal number Y and the boundary of the wheatear in binary image could be obtained. Then the midpoint coordinate of the wheatear boundary was obtained at the trough. And the maximum and minimum point coordinates of the wheatear boundary were obtained at the peak. Then three position points of fitting the parabolic curve for spikelet were ascertained according to the coordinate of peaks and troughs of the smoothing curve at the binary image. Finally,each spikelet in wheatear was segmented using the fitted parabolic curve. The area of each spikelet was extracted. Meanwhile,the grain number of each spikelet was counted manually. So then the relation between the area of each spikelet and the grain number was obtained by using threshold method.[Results]The wheatear images of three wheat varieties were identified to validate the spikelet number and grain number of each wheatear. The experiment results manifested that the average zero error rate of the spikelet number for three wheat varieties was 68.16%,the average absolute error of three wheat varieties of the spikelet number was 0.46,and the average relative error of the spikelet number for three wheat varieties was 2.99% by using aforementioned method to identify the spikelet number at wheatear. The recognition accuracy and the average zero error rate of the spikelet number were greatly improved by compared with the existing literature. And using aforementioned method to identify the grain number at wheatear,the average absolute error of grain number for three wheat varieties was 2.11,and the average relative error of grain number for three wheat varieties was 5.62%.The average measurable time for three wheat varieties was 7.99 s for a wheatear.[Conclusions]The automatically image counting wheat grain number and spikelet number for a wheatear with faster and higher precision can be realized.

参考文献/References:

[1] 杨进文,李亚丽,王曙光,等. 春小麦主要农艺性状与单株产量的相关及通径分析[J]. 山西农业科学,2013,41(5):407-411. Yang J W,Li Y L,Wang S G,et al. The correlation and path analysis between the main agronomic characteristics and single plant yield of spring wheat[J]. Journal of Shanxi Agricultural Sciences,2013,41(5):407-411(in Chinese with English abstract).
[2] 海燕,何宁,康明辉,等. 小麦主要农艺性状的遗传分析[J]. 中国农学通报,2008,24(6):168-171. Hai Y,He N,Kang M H,et al. Genetic analysis of agronomic araits in wheat[J]. Chinese Agricultural Science Bulletin,2008,24(6):168-171(in Chinese with English abstract).
[3] 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. Lu W C,Luo B,Pan D Y,et al. Synchronous measurement of wheat ear length and spikelets number based on image processing[J]. Journal of Chinese Agricultural Mechanization,2016,37(6):210-215(in Chinese with English abstract).
[4] Hruska Z,Yao H B,Kincaid R,et al. Fluorescence imaging spectroscopy(FIS)for comparing spectra from corn ears naturally and artificially infected with aflatoxin producing fungus[J]. Journal of Food Science,2013,78(8):T1313-T1320.
[5] 杜建军,郭新宇,王传宇,等. 基于穗粒分布图的玉米果穗表型性状参数计算方法[J]. 农业工程学报,2016,32(13):168-176. Du J J,Guo X Y,Wang C Y,et al. Computation method of phenotypic parameters based on distribution map of kernels for corn ears[J]. Transactions of the Chinese Society of Agricultural Engineering,2016,32(13):168-176(in Chinese with English abstract).
[6] 周金辉,马钦,朱德海,等. 基于机器视觉的玉米果穗产量组分性状测量方法[J]. 农业工程学报,2015,31(3):221-227. Zhou J H,Ma Q,Zhu D H,et al. Measurement method for yield component traits of maize based on machine vision[J]. Transactions of the Chinese Society of Agricultural Engineering,2015,31(3):221-227(in Chinese with English abstract).
[7] Guo W,Fukatsu T,Ninomiya S. Automated characterization of flowering dynamics in rice using field-acquired time-series RGB images[J]. Plant Methods,2015,11(1):1-14.
[8] 赵三琴,李毅念,丁为民,等. 稻穗结构图像特征与籽粒数相关关系分析[J]. 农业机械学报,2014,45(12):323-328. Zhao S Q,Li Y N,Ding W M,et al. Relative analysis between image characteristics of panicle structure and spikelet number[J]. Transactions of the Chinese Society for Agricultural Machinery,2014,45(12):323-328(in Chinese with English abstract).
[9] 陈兵旗,郭学梅,李晓华. 基于图像处理的小麦病害诊断算法[J]. 农业机械学报,2009,40(12):190-195. Chen B Q,Guo X M,Li X H. Image diagnosis algorithm of diseased wheat[J]. Transactions of the Chinese Society for Agricultural Machinery,2009,40(12):190-195(in Chinese with English abstract).
[10] Crowell S,Falcão A X,Shah A,et al. High-resolution inflorescence phenoltyping using a novel image-analysis pipeline,PANorama[J]. Plant Physiology,2014,165(2):479-495.
[11] 刘连忠,张武,朱诚. 基于改进颜色特征的小麦病害图像识别技术研究[J]. 安徽农业科学,2012,40(26):12877-12879. Liu L Z,Zhang W,Zhu C. Image recognition of wheat diseases based on improved color feature[J]. Journal of Anhui Agricultural Science,2012,40(26):12877-12879(in Chinese with English abstract).
[12] 樊超,夏旭,石小凤,等. 基于图像处理的小麦品种分类研究[J]. 河南工业大学学报(自然科学版),2011,32(5):74-78. Fan C,Xia X,Shi X F,et al. Wheat variety classification based on image processing[J]. Journal of Henan University of Technology(Natural Science Edition),2011,32(5):74-78(in Chinese with English abstract).
[13] Manickavasagan A,Sathya G,Jayas D S. Comparison of illuminations to identify wheat classes using monochrome images[J]. Computers and Electronics in Agriculture,2008,63(2):237-244.
[14] Li Q Y,Cai J H,Berger B,et al. Detecting spikes of wheat plants using neural networks with laws texture energy[J]. Plant Methods,2017,13(83):1-13.
[15] Neethirajan S,Jayas D S,White N D G. Detection of sprouted wheat kernels using soft X-ray image analysis[J]. Journal of Food Engineering,2007,81(3):509-513.
[16] 李明,张长利,王晓楠. 基于图像处理技术的小麦形态检测方法研究[J]. 东北农业大学学报,2009,40(4):111-115. Li M,Zhang C L,Wang X N. Study on the detection system of wheat morphous based on image procession[J]. Journal of Northeast Agricultural University,2009,40(4):111-115(in Chinese with English abstract).
[17] 张玉荣,陈赛赛,周显青,等. 基于图像处理和神经网络的小麦不完善粒识别方法研究[J]. 粮油食品科技,2014,22(3):59-63. Zhang Y R,Chen S S,Zhou X Q,et al. Identification of unsound kernels in wheat based on image processing and neural network[J]. Science and Technology of Cereals,Oils and Foods,2014,22(3):59-63(in Chinese with English abstract).
[18] Zhu Y J,Cao Z G,Lu H,et al. In-field automatic observation of wheat heading stage using computer vision[J]. Biosystems Engineering,2016,143:28-41.
[19] 刘涛,孙成明,王力坚,等. 基于图像处理技术的大田麦穗计数[J]. 农业机械学报,2014,45(2):282-290. Liu T,Sun C M,Wang L J,et al. In-field wheatear counting based on image processing technology[J]. Transactions of the Chinese Society for Agricultural Machinery,2014,45(2):282-290(in Chinese with English abstract).
[20] 范梦扬,马钦,刘峻明,等. 基于机器视觉的大田环境小麦麦穗计数方法[J]. 农业机械学报,2015,46(增刊):234-239. Fan M Y,Ma Q,Liu J M,et al. Counting method of wheatear in field based on machine vision technology[J]. Transactions of the Chinese Society for Agricultural Machinery,2015,46(Suppl):234-239(in Chinese with English abstract).
[21] Cointault F,Guerin D,Guillemin J-P,et al. In-field Triticum aestivum ear counting using colour-texture image analysis[J]. New Zealand Journal of Crop and Horticultural Science,2008,36(2):117-130.
[22] Hughes N,Askew K,Scotson C P,et al. Non-destructive,high-content analysis of wheat grain traits using X-ray micro computed tomography[J]. Plant Methods,2017,13(1):76.
[23] 毕昆,姜盼,李磊,等. 基于形态学图像处理的麦穗形态特征无损测量[J]. 农业工程学报,2010,26(12):212-216. Bi K,Jiang P,Li L,et al. Non-destructive measurement of wheat spike characteristics based on morphological image processing[J]. Transactions of the Chinese Society of Agricultural Engineering,2010,26(12):212-216(in Chinese with English abstract).
[24] 姜盼,张彬,毕昆. 基于图像处理的小麦穗长测量[J]. 中国传媒大学学报(自然科学版),2010,17(4):69-73. Jiang P,Zhang B,Bi K. Wheat ear-length measurements based on image processing[J]. Journal of Communication University of China(Science and Technology),2010,17(4):69-73(in Chinese with English abstract).
[25] 刘璇,王瑞丽,周伟,等. 春季低温对冬小麦穗部发育和粒重的影响[J]. 河南农业大学学报,2013,47(4):373-380. Liu X,Wang R L,Zhou W,et al. Effect of spring low temperature on ear development and grain weight of winter wheat[J]. Journal of Henan Agricultural University,2013,47(4):373-380(in Chinese with English abstract).
[26] 屈会娟,李金才,沈学善,等. 秸秆全量还田对冬小麦不同小穗位和粒位结实粒数和粒重的影响[J]. 中国农业科学,2011,44(10):2176-2183. Qu H J,Li J C,Shen X S,et al. Effects of all straw returned to the field on grain number and grain weight at different spikelets and grain positions in winter wheat[J]. Scientia Agricultura Sinica,2011,44(10):2176-2183(in Chinese with English abstract).
[27] 程洁,周荣全,吴玉川,等. 不同水分条件下小麦穗部性状的遗传分析[J]. 华北农学报,2015,30(增刊):146-151. Cheng J,Zhou R Q,Wu Y C,et al. Genetic analysis of spike traits in wheat cultivated in contrasted water conditions in wheat[J]. Acta Agriculturae Boreali-Sinica,2015,30(Suppl):146-151(in Chinese with English abstract).
[28] Hu Y S,Ren T H,Li Z,et al. Molecular mapping and genetic analysis of a QTL controlling spike formation rate and tiller number in wheat[J]. Gene,2017,634:15-21.

备注/Memo

备注/Memo:
收稿日期:2017-09-26。
基金项目:江苏省政策引导类计划(产学研合作)项目(BY2016060-01);国家重点研发计划项目(2016YFD0300908)
作者简介:杜世伟,硕士研究生。
通信作者:李毅念,副教授,研究方向为现代农业装备研究,E-mail:liyinian@163.com
更新日期/Last Update: 1900-01-01