本文已被：浏览 2069次 下载 0次
投稿时间：2011-10-14 修订日期：2012-03-26
投稿时间：2011-10-14 修订日期：2012-03-26
中文摘要: 针对磁瓦表面缺陷对比度低、自动识别困难的问题，作者提出了一种对磁瓦图像应用快速离散Curvelet变换（FDCT）提取特征，并用支持向量机（SVM）分类器进行分类的磁瓦微小缺陷自动识别方法。该方法首先对磁瓦图像做分块处理，并对各分块图像应用FDCT，计算分解系数的l^2范数，获得磁瓦不同方向的纹理频域特征；然后以归一化的分解系数l^2范数作为支持向量机分类器的特征向量，对图像做出分类。对不同缺陷占比的图像进行实验测试，结果显示，当缺陷部分占分块图像的比例在1/64以上时正确识别率大于83%。
中文关键词: Curvelet变换 表面缺陷 纹理 支持向量机
Abstract:Difficulties exist in automatically inspecting surface defects because of the low intensity image contrast. To overcome these difficulties, a textures analysis method for detecting defects on the magnetic tile surfaces was described. In this methodology the original image was divided into several equal sized squares, and decomposed based on a fast discrete curvelet transform (FDCT) at different scales and orientations. Then thel^2norms on the curvelet coefficients were calculated as the feature vector for support vector machine (SVM) classifier. The experimental results showed that the defects retrieval accuracy achieved 83% when defects accounted for more than 1/64 of magnetic tile image.
文章编号：201100910 中图分类号： 文献标志码：
基金项目:国家科技支撑计划课题资助项目（2006BAF01A07）；四川省高新技术产业重大关键技术资助项目（2010GZ0051)
作者简介:
引用文本：
蒋红海,殷国富,刘培勇,尹湘云.基于Curvelet变换和支持向量机的磁瓦表面缺陷识别方法[J].工程科学与技术,2012,44(3):147-152.
Jiang Honghai,Yin Guofu,Liu Peiyong,Yin Xiangyun.Defect Detection on Magnetic Tile Surfaces Based on Fast Discrete Curvelet Transform and Support Vector Machine[J].Advanced Engineering Sciences,2012,44(3):147-152.
引用文本：
蒋红海,殷国富,刘培勇,尹湘云.基于Curvelet变换和支持向量机的磁瓦表面缺陷识别方法[J].工程科学与技术,2012,44(3):147-152.
Jiang Honghai,Yin Guofu,Liu Peiyong,Yin Xiangyun.Defect Detection on Magnetic Tile Surfaces Based on Fast Discrete Curvelet Transform and Support Vector Machine[J].Advanced Engineering Sciences,2012,44(3):147-152.