Please use this identifier to cite or link to this item:
Title: Defects recognition of microlens array using gabor filters and supported vector machine
Other Titles: 微镜阵列的缺陷提取与识别
Authors: Hu, K
Cheung, CF 
Jiang, XQ
Kong, LB
Keywords: MLA
Gabor filters
Issue Date: 2009
Publisher: 中國學術期刊 (光盤版) 電子雜誌社
Source: 组合机床与自动化加工技术 (Modular machine tool & automatic manufacturing technique), 2009, no. 9, p. 7-10, 14 How to cite?
Journal: 组合机床与自动化加工技术 (Modular machine tool & automatic manufacturing technique) 
Abstract: 微镜阵列作为现在广泛应用的一种微米量级的微小型光学元件,缺陷识别是其加工制造的一个重要问题。文章着重于微镜特征提取和微镜阵列的评定。使用Gabor滤波和灰度共生矩阵提取缺陷特征,提出了基于支持向量机的多类分类缺陷识别方法.根据统计学原理,使用核函数将样本映射到高维空间进行训练.综合各种核函数的测试准确率,得到解决该问题的最佳核函数.通过比较不同的多类分类算法,提出了基于DAGSVM的诊断模型。并通过不同的特征向量与和不同的分类器的比较,实验结果表明该方法识别率高,识别速度快,容错性好,而且能够正确识别有缺陷的微镜图像。
Defects recognition is an important problem with application to fabrication of MLA(Microlens Array).The focus of this paper is on the problem of feature extraction and classification for defects recognition of MLA.Specifically,we propose using Gabor filters for MLA feature extraction and SVM(Support Vector Machine) for defects detection.a multi-classification method based on support vector machine(SVM) is proposed.According t o statistic learning theory,we use kernel functions to map the training samples into a high dimensional space for training.Combining the testing accuracy of different kernel functions,an optimal kernel function is obtained to solve this problem.By comparing different multi-calssification strategies,a diagnosis model based on DAGS VM(directed acyclic graph SVM) is constructed.Extensive experimentation and comparisons using real data,different features and different classifiers(e.g.,Neural Networks and Support Vector Machine) demonstrate the superiority of the proposed approach which has achieved an average accuracy. 还原
ISSN: 1001-2265
Rights: © 2009 中国学术期刊电子杂志出版社。本内容的使用仅限于教育、科研之目的。
© 2009 China Academic Journal Electronic Publishing House. It is to be used strictly for educational and research purposes.
Appears in Collections:Journal/Magazine Article

Files in This Item:
File Description SizeFormat 
r45765.pdf422.34 kBAdobe PDFView/Open
View full-text via PolyU eLinks SFX Query
Show full item record
PIRA download icon_1.1View/Download Contents

Page view(s)

Last Week
Last month
Citations as of Feb 18, 2019


Citations as of Feb 18, 2019

Google ScholarTM


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.