| 基于特征提取的缺陷图像分类方法 |
| |
| 引用本文： | 张国翊,胡铮,徐婷.基于特征提取的缺陷图像分类方法[J].北京工业大学学报,2010,36(4). |
| |
| 作者姓名： | 张国翊 胡铮 徐婷 |
| |
| 作者单位： | 1. 北京邮电大学泛网无线通信教育部重点实验室,北京,100876
2. 北京工业大学交通工程重点实验室,北京,100124 |
| |
| 基金项目： | 国家自然科学基金资助项目(60372047) |
| |
| 摘 要： | 针对缺陷图像表面复杂多变、特征不宜提取的特点,提出了一种归一化转动惯量特征和不变矩特征相结合的时域分析方法来构建缺陷图像的统计特征量,同时增加缺陷矩形框区域内压缩度、距离极值比和线度特征量作为缺陷分类的依据;提出了在缺陷频谱图像内提取特征量的频域分析方法,并将矩形框区域内所有像素点灰度平均值和灰度方差值作为缺陷分类的另一重要依据;同时将BP神经网络应用于缺陷图像的自动分类中,构建了系统的缺陷分类器,并对现场采集的常见6种缺陷类型进行了实验.结果表明,该特征提取方法在很大程度上提高了特征的分类有效性;该BP分类器识别率较高,现场整体识别率达到90%以上,在一定程度上解决了缺陷图像分类难的问题.
|
| 关 键 词： | 缺陷图像 特征提取 缺陷分类 BP神经网络 |
Classification Method for Defect Image Based on Feature Extraction |
| |
| ZHANG Guo-yi,HU Zheng,XU Ting.Classification Method for Defect Image Based on Feature Extraction[J].Journal of Beijing Polytechnic University,2010,36(4). |
| |
| Authors: | ZHANG Guo-yi HU Zheng XU Ting |
| |
| Affiliation: | 1.Key Laboratory of Universal Wireless Communications Ministry of Education;Beijing University of Posts and Telecommunications;Beijing 100876;China;2.Key Lab of Traffic Engineering;Beijing University of Technology;Beijing 100124;China |
| |
| Abstract: | Being aimed at the characteristic in complexity and levity of defect image surface,a novel method combined NMI feature with invariant feature in time domain to conceive the statistic feature of defect images is put forward.Simultaneously,compactness feature,L-S factor feature and linearity feature in the rectangular region are developed as one basis of defect classification.Moreover,in frequency domain,a method which can extract features in the rectangular region of central bright area of defect spectrum im... |
| |
| Keywords: | defect image feature extraction defect classification BP neural network |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
|
