基于GWO优化SVM的小麦籽粒优劣分级研究

doi:10.16035/j.issn.1001-7283.2021.01.028

作物杂志,2021, 第1期: 200–206 doi: 10.16035/j.issn.1001-7283.2021.01.028

• 农业信息技术 • 上一篇

基于GWO优化SVM的小麦籽粒优劣分级研究

安娟华(), 董鑫, 王克俭(), 何振学

河北农业大学信息科学与技术学院,071000,河北保定

收稿日期:2020-03-18 修回日期:2020-05-08 出版日期:2021-02-15 发布日期:2021-02-23
通讯作者: 王克俭
作者简介:安娟华,主要从事图像处理研究,E-mail： 2193166210@qq.com
基金资助:
河北省教育厅重点研究项目(ZD2016158)

Study on the Classification of Wheat Grain Quality Based on GWO Optimized SVM

An Juanhua(), Dong Xin, Wang Kejian(), He Zhenxue

College of Information Science and Technology, Hebei Agricultural University, Baoding 071000, Hebei, China

Received:2020-03-18 Revised:2020-05-08 Online:2021-02-15 Published:2021-02-23
Contact: Wang Kejian

摘要/Abstract

摘要：

小麦籽粒优劣不仅是产量及品质的重要决定因素,也是育种适应性的综合指标。为了提高小麦籽粒优劣分级的准确率,同时克服神经网络中存在的收敛速度慢、容易陷入局部极值等缺陷,提出一种灰狼算法（GWO）优化支持向量机（SVM）的小麦籽粒优劣分级方法,以航麦8805为研究对象,利用图像处理技术对小麦籽粒图像进行预处理并提取小麦籽粒的形态、颜色和纹理等21个特征。然后采用灰狼算法对支持向量机的两个参数（c、σ）进行优化,建立GWO-SVM模型,从而对小麦籽粒进行优劣分级。与其他算法相比,GWO优化SVM的算法对小麦籽粒的分级准确率有明显的提高,对小麦籽粒优劣分级的准确率可达到95.08%。

关键词: 小麦籽粒, 优劣分级, 灰狼优化算法, 支持向量机

Abstract:

Wheat grain quality is not only an important determinant of yield and quality but also a comprehensive indicator of breeding adaptability. In order to improve the accuracy of wheat grain grading, at the same time to solve the problem of local optimal solution and slow convergence rate existed in artificial neural networks, we presented a method based on support vector machine (SVM) with gray wolf algorithm optimization (GWO) for grading of wheat grain. First of all to wheat 8805 as the research object, using the image processing technology of wheat grain image preprocessing and extract the grain morphology, color, texture, a total of 21 characteristics. Then, GWO was used to optimize the two parameters (c, σ) of the SVM, and the GWO-SVM model was established to grading of wheat grains. Comparing the GWO optimized SVM algorithm with other algorithms, the results showed that the accuracy of the GWO optimized SVM algorithm for wheat grain classification can reach 95.08%, which is significantly higher than other algorithms.

Key words: Wheat grain, Classification of advantages and disadvantages, Grey wolf optimizer, Support vector machine

安娟华, 董鑫, 王克俭, 何振学. 基于GWO优化SVM的小麦籽粒优劣分级研究[J]. 作物杂志, 2021 (1): 200–206

An Juanhua, Dong Xin, Wang Kejian, He Zhenxue. Study on the Classification of Wheat Grain Quality Based on GWO Optimized SVM[J]. Crops, 2021(1): 200–206

图/表 5

图1

图2

表1

表2

表3

参考文献 21

[1]	赵广才, 常旭红, 王德梅. 小麦生产概况及其发展. 作物杂志, 2018(4):1-7.
[2]	王一丁, 李霁阳. 谷物外观品质检测方法的研究. 计算机测量与控制, 2017,18(2):35-38.
[3]	Zayas I Y, Pomeranz Y, Lai F S. Discrimination between Arthur and Arkan wheats by image analysis. Cereal Chemistry, 1985,629(2):52-56.
[4]	Verma B. Image processing techniques for grading & classification of rice. International Conference on Computer and Communication Technology 2010,Punjab India, IEEE, 2010: 220-223.
[5]	Paliwal J, Visen N S, Jayas D S. Cereal grain and dockage identification using machine vision. Biosytems Engineering, 2003,85(1):51-57.
[6]	Mahale B, Korde S. Rice quality analysis using image processing techniques. Convergence of Technology. IEEE, 2014: 1-5.
[7]	Abirami S, Neelamegam P, Kala H. Analysis of rice granules using image processing and neural network pattern recognition tool. Journal of Electrostatics, 2015,76(8):20-24.
[8]	Waghmare H, Kokare R, Dandawate Y. Detection and classification of diseases of Grape plant using opposite colour Local Binary Pattern feature and machine learning for automated Decision Support System. International Conference on Signal Processing and Integrated Networks 2016, New Delhi India, 2016: 513-518.
[9]	石小风. 基于图像处理的小麦外观品质检测与分级. 郑州:河南工业大学, 2013.
[10]	梁良. 基于改进层次分析法小麦籽粒优劣分级技术研究. 保定:河北农业大学, 2015.
[11]	冯丽娟, 李秀娟, 文成林. 基于稀疏表示的小麦品种识别. 江南大学学报, 2015,14(6):730-735.
[12]	孟惜, 王克俭, 韩宪忠. 基于改进BP网络的小麦品种识别. 贵州农业科学, 2017,45(10):156-160.
[13]	张博. 基于深度学习的小麦外观品质机器视觉检测研究. 杨凌:西北农林科技大学, 2019.
[14]	张浩, 李和平, 叶娟. 小麦籽粒外观形态特征测定技术研究. 粮食与饲料工业, 2013(3):7-9.
[15]	张恒敢, 杨四军, 顾克军. 应用数字图像处理获取小麦子粒外观特征参数的方法及其Matlab实现. 江苏农业科学, 2005(1):28-31.
[16]	张恒敢, 杨四军. 应用数字图像处理获取小麦籽粒颜色特征参数. 安徽农业科学, 2008,36(9):3582-3583.
[17]	王志军, 丛培盛. 基于图像处理与人工神经网络的小麦颗粒外观品质评价方法. 农业工程学报, 2007,23(1):158-161.
[18]	谭贵生, 石宜金. 基于混沌粒子群优化支持向量机的变压器故障诊断. 昆明理工大学学报(自然科学版), 2019,44(5):54-61.
[19]	邹心遥, 陈敬伟, 姚若河. 采用粒子群优化的SVM算法在数据分类中的应用. 华侨大学学报, 2016,37(2):171-174.
[20]	燕志星, 王海瑞, 吕维宗. 基于GWO-SVM算法的滚动轴承故障诊断. 化工自动化及仪表, 2019,46(10):806-810.
[21]	王志华, 罗奇, 刘绍庭. 基于混沌灰狼优化算法的SVM分类器研究. 计算机工程与科学, 2018,40(11):2040-2046.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed

等级 Grade	人工分级结果(粒) Manual grading results (grain)	GWO-SVM
等级 Grade	人工分级结果(粒) Manual grading results (grain)	正确分级数(粒) Number of correct grades (grain)	错误分级数(粒) Number of error ratings (grain)	正检率 Correct detection rate (%)	错检率 False detection rate (%)
优Superior	29	28	1	96.55	3.45
中Medium	20	19	1	95.00	5.00
劣Inferior	12	11	1	91.67	8.33
总计Total	61	58	3	95.08	4.92
均值Mean	-	-	-	94.41	5.59

算法 Algorithm	等级 Grade	正确分级数(粒) Number of correct grades (grain)	错误分级数(粒) Number of error ratings (grain)	正检率 Correct detection rate (%)	错检率 False detection rate (%)
PSO-SVM	优Superior	28	1	96.55	3.45
	中Medium	17	3	85.00	15.00
	劣Inferior	10	2	83.33	16.67
	总计Total	55	6	90.16	9.84
	均值Mean	-	-	88.29	11.71
SVM	优Superior	26	3	89.66	10.34
	中Medium	15	5	75.00	25.00
	劣Inferior	10	2	83.33	16.67
	总计Total	51	10	83.61	16.39
	均值Mean	-	-	82.66	17.34

K值K-value	SVM	GWO-SVM	PSO-SVM
3	1.68	4.27	12.27
5	2.72	4.86	14.86
7	3.20	5.01	15.01

基于GWO优化SVM的小麦籽粒优劣分级研究

Study on the Classification of Wheat Grain Quality Based on GWO Optimized SVM

RichHTML

PDF (PC)

摘要/Abstract

引用本文

使用本文

图/表 5

参考文献 21

相关文章 4

Metrics

本文评价

推荐阅读 10

[1]	陈孝, 辛志勇, 肖世和, 等. 黄矮病对小麦产量性状的影响[J]. 作物杂志, 1995, (2): 5–6
[2]	张玉良, 王文真, 王光瑞. 小麦籽粒硬度测定方法的研究[J]. 作物杂志, 1992, (3): 40–封三
[3]	邓良均. 对白粒小麦优价政策的商榷[J]. 作物杂志, 1985, (3): 38–39
[4]	章学澄. 谈谈两种不同的小麦制粉加工方法[J]. 作物杂志, 1985, (2): 24–25