[1]朱伟兴,苏威,张怀德.基于支持向量机的重叠大豆颗粒计数[J].大豆科学,2009,28(01):151-155.[doi:10.11861/j.issn.1000-9841.2009.01.0151]
　ZHU Wei-xing,SU Wei,ZHANG Huai-de.Counting of Overlapping Soybean Grain by Support Vector Machine[J].Soybean Science,2009,28(01):151-155.[doi:10.11861/j.issn.1000-9841.2009.01.0151]
点击复制

基于支持向量机的重叠大豆颗粒计数

《大豆科学》[ISSN:1000-9841/CN:23-1227/S] 卷: 第28卷 期数: 2009年01期 页码: 151-155 栏目: 出版日期: 2009-02-25
Title:
Counting of Overlapping Soybean Grain by Support Vector Machine
文章编号:
1000-9841(2009)01-0151-05
作者:
朱伟兴; 苏威; 张怀德
江苏大学电气信息工程学院，江苏 镇江 212013
Author(s):
ZHU Wei-xing; SU Wei; ZHANG Huai-de
Electrical and Information Engineering College，Jiangsu University，Zhenjiang 212013，Jiangsu，China
关键词:
支持向量机; 分割; 计数; 大豆
Keywords:
Support Vector Machine; Segment; Count; Soybean
分类号:
TP391.41
DOI:
10.11861/j.issn.1000-9841.2009.01.0151
文献标志码:
A
摘要:
为了提高大豆千粒重的测定效率和精度，提出一种基于机器视觉的有效分割多层重叠颗粒和记数方法。将由摄像机采集的大豆颗粒图像经预处理后，提取所有的颗粒块区域；寻找颗粒块区域的拓扑形状特征欧拉数和形状特征向量：颗粒块轮廓边缘上凹点、颗粒块类圆近似核心；采用支持向量机分类法智能识别颗粒叠加类型，将其分为串重叠、多个并粘连和两层并重叠，最后实现自动分割。结果表明：该方法能有效解决两层重叠或深度粘连类圆大豆颗粒的准确计数。
Abstract:
In order to improve the efficiency and precision for measuring the mass of 1 000 soybean grains，a novel new method which can effectively segment overlapping granule and count it based on the machine vision technique was proposed.Firstly collecting the products grain image and be preprocessed，then distilling the region of all overlapping grain；The concave points，grains’ approximate center of area and the euler number of topology shape were found out as the feature vectors of the overlapping area；the types of overlapping particle intellectively were finally identified into serial，parallel and double-deck overlapping types by the classification of Support Vector Machine，and automatically divided overlapping granule into lots of single grains.The experimental results show that the paper can effectively count the double-deck overlapping or profoundly cohesive soybean grains.

参考文献/References:

[1]杨蜀秦，何东健．连接大米籽粒图像的自动分割算法研究[J]．农机化研究，2005(5)：62-65．(Yang S Q，He D J.Automated identification and separation of touching rice grains with machine vision[J].Agricultural Mechanize Research，2005(5)：62-65.)

[2] Roerdink J B，Meijster A.The watershed transform：definitions，algorithms and strategies[J].Fundamental Information，2001，41：187-288．
[3]凌云，王一鸣，孙明，等.基于流域算法的谷物籽粒图像分割技术[J]．农业机械学报，2005，36(3)：95-98．(Lin Y，Wang Y L，Sun M，et al.Application of watershed algorithm to paddy image segmentation[J].Journal of Agricultural Machine，2005，36(3)：95-98.)
[4] Wang W．Study on cell cluster splitting[J].IEEE Computer Society，2007，183：427-432．
[5]赵杰文，刘少鹏，邹小波，等.基于支持向量机的缺陷红枣机器视觉识别[J]．农业机械学报，2008，39(3)：113-116.(Zhao J W，Liu S P，Zhou X B，et al.Recognition of defect Chinese dates by machine vision and support vector machine[J].Journal of Agricultural Machine，2008，39(3)：113-116.)
[6]傅蓉，申洪，陈浩.基于凹点搜寻的重叠细胞图像自动分离的算法研究[J]．计算机工程与应用，2007，43(17)：21-24．(Fu R，Shen H，Chen H.Research of automatically separating algorithm for overlap cell based on searching concave spot[J].Computer Engineering and Applications，2007，43(17)：21-24.)
[7] Ioannou D，Huda W，Laine A F．Circle recognition through a 2D hough transform and radius histogramming[J]．Image and Vision Computing，1999，17：15-26．
[8]林金龙，石青云．用点Hough变换实现圆检测的方法[J]．计算机工程，2003，29(11)：17-19．(Lin J L，Shi Q Y.Circle recognition through a point Hough transformation[J].Computer Engineering，2003，29(11)：17-19.)
[9]罗三定，肖飞.不规则类圆形团块目标图像识别的新方法[J].中南大学学报，2002，35(4)：632-637．(Luo S D，Xiao F.A new method of recognizing quasi circular object[J].Journal of South University，2002，35(4)：632-637.)
[10]雷国伟，郭东辉.基于CNN二值图像处理的欧拉数计算[J].哈尔滨工程大学学报，2006，27(10)：202-204．(Lei G W，Guo D H.Euler solving based on binary image processing via CNN[J].Journal of Harbin Institute of Technology，2006，27(10)：202-204.)
[11]王立国，张晔，谷延锋.支持向量机多类目标分类器的结构简化研究[J]．中国图象图形学报，2005，10(5)：571-574．(Wang L G，Zhang Y，Gu Y F.Research of simplification of structure of multi class classifier of SVM[J].Journal of Image and Graphics，2005，10(5)：571-574.)
[12] Vapnik V N.Statistical learning theory[M].New York，John Wiley，1998，95-104.
[13] HSU C W，L IN C J.A comparison of methods for multi class support vector machines [J].IEEE Transon Neural Networks，2002，13（2）：415-425.

备注/Memo

基金项目：江苏大学江苏省现代农业装备与技术重点实验室开放基金资助项目(NZ200709)。

作者简介：朱伟兴(1956-),男,教授,博士生导师，主要研究方向为智能控制与检测技术。
通讯作者：苏威。E-mail:2002110113@163.com。

更新日期/Last Update: 2014-10-03