基于混合染色体的带钢缺陷图像分类方法研究

J4 ›› 2016, Vol. 38 ›› Issue (06): 1213-1219.

基于混合染色体的带钢缺陷图像分类方法研究

刘亚，胡慧君，刘茂福

(1.武汉科技大学计算机科学与技术学院，湖北武汉 430065;
2.武汉科技大学智能信息处理与实时工业系统湖北省重点实验室，湖北武汉 430065)

收稿日期:2015-01-23 修回日期:2015-08-19 出版日期:2016-06-25 发布日期:2016-06-25
基金资助:
国家自然科学基金（61100133）；湖北省重点实验室开放基金（znss2013B014）

Strip steel surface defects classification
based on hybrid chromosome

LIU Ya,HU Huijun,LIU Maofu

（1.College of Computer Science and Technology,Wuhan University of Science and Technology,Wuhan 430065;
2.Hubei Province Key Laboratory of Intelligent Information Processing and Realtime Industrial System,
Wuhan University of Science and Technology,Wuhan 430072,China)

Received:2015-01-23 Revised:2015-08-19 Online:2016-06-25 Published:2016-06-25

摘要/Abstract

摘要：

为了保证带钢缺陷分类的实时性和准确性，提出了一种基于混合染色体的带钢缺陷图像分类方法。该方法不仅优化了支持向量机SVM中核函数参数、惩罚因子，并且对核函数、输入的特征向量进行了选择。除此之外，该方法融合了遗传算法和SVM，用遗传算法优化影响SVM的核函数参数、惩罚因子、输入特征和核函数；同时，用SVM建立的分类模型的分类准确率限制遗传算法的进化方向，彼此制约和促进，最终确定最优分类模型。实验结果表明，基于混合染色体的带钢缺陷图像分类方法建立的分类模型能实时、准确地对带钢缺陷图像进行分类。

关键词: 带钢缺陷分类, 混合染色体, SVM, 遗传算法, 分类准确率

Abstract:

In order to guarantee the characteristics of real time and accuracy in strip steel defect classification, we propose a defect classification model based on hybrid chromosome for the strip steel surface image. This method not only optimizes both the kernel function parameters and the penalty factors of the support vector machine (SVM) model, but also makes choice of feature vectors and kernel functions. Meanwhile, the genetic algorithm and the SVM model are fused and the final SVM classifier is established by using the decoding results of the optimal chromosome in the end. Experimental results show that our method is effective and efficient in classifying the defects in the strip steel surface image.

Key words: strip steel surface defect classification;hybrid chromosome;SVM;genetic algorithm;classification accuracy

刘亚，胡慧君，刘茂福. 基于混合染色体的带钢缺陷图像分类方法研究[J]. J4, 2016, 38(06): 1213-1219.

LIU Ya,HU Huijun,LIU Maofu. Strip steel surface defects classification
based on hybrid chromosome [J]. J4, 2016, 38(06): 1213-1219.

参考文献［18］

［1］	Hu Huijun,Li Yuanxiang,Liu Maofu,et al.Steel strip surface defects classification based on machine learning［J］.Computer Engineering and Design,2014,35(2):620624.(in Chinese)
［2］	Tang Bo, Kong Jianyi, Wang Xingdong, et al.Recognition and classification for steel strip surface defect images based on rough set theory［J］.Journal of Image and Graphics,2011,16(7):12131218.(in Chinese)
［3］	Chen Yue,Zhang Xiaoguang.Classification of surface defect images of steel strip by extenics theory［J］.Computer Engineering and Applications,2013,49(21):2428.(in Chinese)
［4］	Fu Yan, Wang Yaowei, Wang Weiqiang, et al. Contentbased natural image classification and retrieval using SVM［J］.Chinese Journal of Computers,2003,26(10):12611265.(in Chinese)
［5］	Chen Rong,Cao Yongfeng,Sun Hong,et al.Multiclass image classification with active learning and semisupervised learning［J］.Journal of Automatica Sinica,2011,37(8):954962.(in Chinese)
［6］	Huang C L,Wang C J.A GAbased feature selection and parameters optimization for support vector machines［J］.Expert Systems with Applications,2006,31(2):231240.
［7］	Zhao M,Fu C,Ji L,et al.Feature selection and parameter optimization for support vector machines:A new approach based on genetic algorithm with feature chromosomes［J］.Expert Systems with Applications,2011,38(5):51975204.
［8］	Gonzalez R C. Digital image processing［M］.3rd Edition. Beijing:Publishing House of Electronics Industry,2010.
［9］	Zhang Jing,Li Yibing,Li Ao.An image enhancement method based on dualtree complex wavelet transform［J］.Computer Engineering & Science,2012,33(11):98102.(in Chinese)
［10］	Zhang J, Zhan Z, Lin Y, et al.Evolutionary computation meets machine learning:A survey［J］.IEEE Computational Intelligence Magazine,2011,6(4):6875.
［11］	Bolaos R,Echeverry M,Escobar J.A multiobjective nondominated sorting genetic algorithm (NSGAII) for the multiple traveling salesman problem［J］.Decision Science Letters,2015,4(4):559568.
［12］	Du Zhuoming,Geng Guohua,Xu Peng,et al.Application of improved genetic algorithms in realtime differential image motion picture processing［J］.Pattern Recognition and Artificial Intelligence,2012,25(5):879884.(in Chinese)
［13］	Zhu Yingying, Yin Chuanhuan, Mu Shaomin. An improved algorithm of local support vector machine［J］.Computer Engineering & Science,2013,35(2):9195.(in Chinese)
［14］	Chang C C,Lin C J.LIBSVM:A library for support vector machines［J］.ACM Transactions on Intelligent Systems and Technology (TIST),2011,2(3):27.
［15］	Elghazal A,Basir O,Belkasim S.Invariant curvaturebased Fourier shape descriptors［J］.Journal of Visual Communication and Image Representation,2012,23(4):622633.
［16］	Hu M K.Visual pattern recognition by moment invariants［J］.IRE Transactions on Information Theory,1962,8(2):179187.
［17］	Guo Z,Zhang L,Zhang D.Rotation invariant texture classification using LBP variance (LBPV) with global matching［J］.Pattern Recognition,2010,43(3):706719.
［18］	Ren Guozhen,Jiang Tao.Stuy on GLCMbased texture extraction methods［J］.Computer Applications and Software,2014,31(11):190192.(in Chinese)
［19］	Nakagawa T,Iwahori Y,Bhuyan M K.Defect classification of electronic board using multiple classifiers and grid search of SVM parameters［J］.Computer and Information Science,2013,493(1):115127.
	附中文参考文献：
［1］	胡慧君,李元香,刘茂福,等.基于机器学习的带钢表面缺陷分类方法研究［J］.计算机工程与设计,2014,35(2):620624.
［2］	汤勃,孔建益,王兴东,等.粗糙集理论的带钢表面缺陷图像的识别与分类［J］.中国图象图形学报,2011,16(7):12131218.
［3］	陈跃,张晓光.带钢表面缺陷图像的可拓分类算法［J］.计算机工程与应用,2013,49(21):2428.
［4］	付岩,王耀威,王伟强,等.SVM用于基于内容的自然图像分类和检索［J］.计算机学报,2003,26(10):12611265.
［5］	陈荣,曹永锋,孙洪,等.基于主动学习和半监督学习的多类图像分类［J］.自动化学报,2011,37(8):954962.
［9］	张静,李一兵,李骜.基于双树复小波变换的图像增强方法［J］.计算机工程与科学,2012,33(11):98102.
［12］	杜卓明,耿国华,徐鹏,等.改进遗传算法在差分像运动图像实时处理中的应用［J］.模式识别与人工智能,2012,25(5):879884.
［13］	朱莹莹,尹传环,牟少敏.一种改进的局部支持向量机算法［J］.计算机工程与科学,2013,35(2):9195.
［18］	任国贞,江涛.基于灰度共生矩阵的纹理提取方法研究［J］.计算机应用与软件,2014,31(11):190192.

[1]	韩辉, 麦合甫热提, 吾尔尼沙·买买提, 朱亚俐, 库尔班·吾布力, . 基于Gist和IPCA算法的多文种离线手写签名识别[J]. 计算机工程与科学, 2022, 44(11): 2048-2055.
[2]	文武, 万玉辉, 文志云, . 基于正余弦算法的文本特征选择[J]. 计算机工程与科学, 2022, 44(08): 1467-1473.
[3]	毛媛媛, 石恩雅, 蒋从锋, 仇烨亮, 贾刚勇, 万健, 闫龙川. 基于遗传算法的数据中心能效仿真[J]. 计算机工程与科学, 2021, 43(08): 1341-1352.
[4]	胡新荣, 刘嘉文, 刘军平, 彭涛, 何儒汉, . 基于改进GA-BP-MC神经网络的人体三维尺寸预测[J]. 计算机工程与科学, 2021, 43(08): 1443-1453.
[5]	李静, 莫思敏 . 基于改进遗传算法的深度神经网络优化研究[J]. 计算机工程与科学, 2021, 43(08): 1503-1511.
[6]	徐周波, 李萍, 刘华东, 李珍. 基于图嵌入与拓扑结构信息的蛋白质复合物识别算法[J]. 计算机工程与科学, 2021, 43(06): 1052-1059.
[7]	党小超, 汝春瑞, 郝占军, . 基于CSI与SVM回归的室内定位方法[J]. 计算机工程与科学, 2021, 43(05): 853-861.
[8]	李晶晶, 许少华. 基于组合核函数的径向基过程神经网络及其在示功图诊断中的应用[J]. 计算机工程与科学, 2021, 43(04): 746-752.
[9]	季子豪, 江凌云. 一种基于遗传算法的多站点协同计算卸载算法[J]. 计算机工程与科学, 2021, 43(03): 426-434.
[10]	贾俊杰, 秦海涛. 基于遗传算法的动态轨迹匿名算法[J]. 计算机工程与科学, 2021, 43(01): 142-150.
[11]	李丹莲, 曹倩, 徐菲. 基于改进遗传算法的连锁便利店配送路径优化[J]. 计算机工程与科学, 2020, 42(11): 2096-2102.
[12]	陈旺虎，田真，张礼智，梁小燕，高雅琼. 基于插值的高维稀疏数据离群点检测方法[J]. 计算机工程与科学, 2020, 42(06): 966-972.
[13]	王硕禾1，刘旭1，李苏晨1，张国驹2. 基于多目标遗传算法的LoRa参数匹配优化[J]. 计算机工程与科学, 2020, 42(03): 434-440.
[14]	葛晓伟, 李凯霞, 程铭. 基于CNN-SVM的护理不良事件文本分类研究[J]. 计算机工程与科学, 2020, 42(01): 161-166.
[15]	周忠眉1,2,李家辉1,2. 基于各类支持度阈值独立挖掘的关联改进算法[J]. 计算机工程与科学, 2019, 41(11): 2088-2094.