| 不变矩法分类识别带钢表面的缺陷 |
| |
| 引用本文： | 张媛,程万胜,赵杰. 不变矩法分类识别带钢表面的缺陷[J]. 光电工程, 2008, 35(7): 90-94 |
| |
| 作者姓名： | 张媛 程万胜 赵杰 |
| |
| 作者单位： | 哈尔滨工业大学,机器人技术与系统国家重点实验室,哈尔滨,150080;哈尔滨工业大学,机器人技术与系统国家重点实验室,哈尔滨,150080;哈尔滨工业大学,机器人技术与系统国家重点实验室,哈尔滨,150080 |
| |
| 基金项目： | 教育部长江学者和创新团队发展计划 |
| |
| 摘 要： | 针对带钢表面缺陷的识别和分类技术,本文采用一种将不变矩与主成分分析法相结合的特征提取方法.首先,对每幅缺陷图像提取22 维不变矩特征向量,满足对图像平移、尺度及旋转变化都不敏感;然后,为了提高分类器的效率,应用主成分分析法对特征向量进行空间降维处理,得到4 维特征向量;最后,将特征向量作为BP神经网络的输入,对网络进行权值和阈值训练,达到缺陷分类的目的.实验结果表明,该方法对带钢表面缺陷的平均正确识别率可达到85%以上.
|
| 关 键 词： | 不变矩 主成分分析法 BP 神经网络 特征提取 带钢表面缺陷 |
| 收稿时间： | 2007-09-17 |
Classification of Surface Defects of Strips Based on Invariable Moment Functions |
| |
| ZHANG Yuan,CHENG Wan-sheng,ZHAO Jie. Classification of Surface Defects of Strips Based on Invariable Moment Functions[J]. Opto-Electronic Engineering, 2008, 35(7): 90-94 |
| |
| Authors: | ZHANG Yuan CHENG Wan-sheng ZHAO Jie |
| |
| Affiliation: | ZHANG Yuan,CHENG Wan-sheng,ZHAO Jie ( State Key Laboratory of Robotics , System,Harbin Institute of Technology,Harbin 150080,China ) |
| |
| Abstract: | A method of feature extraction which is composed of invariable moment functions and Principal Component Analysis (PCA) is presented in order to recognize and classify the surface defects of strips. First, a 22-dimensional eigenvector which was invariable was extracted from images when the image was translated, scaled and rotated. And then, in order to improve the efficiency of classification, PCA was applied to reduce the dimension of the eigenvector. As a result, the 4-dimensional eigenvector was obtained.... |
| |
| Keywords: | invariable moment PCA BP neural network feature extraction surface defect of strips |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
|
