Multivariate Image Analysis in Gaussian Multi-Scale Space for Defect Detection

作     者：Dong-tai Liang~1 Wei-yan Deng~2 Xuan-yin Wang~1 Yang Zhang~11.State Key Laboratory of Fluid Power Transmission and Control Zhejiang University,Hangzhou 310027,P.R.China2.College of Mechanical and Electrical Engineering,China Jiliang University,Hangzhou 310018,P.R.China 

作者机构：[a]State Key Laboratory of Fluid Power Transmission and Control Zhejiang University Hangzhou 310027 P. R. China [b]College of Mechanical and Electrical Engineering China Jiliang University Hangzhou 310018 P. R. China 

出 版 物：《Journal of Bionic Engineering》 (仿生工程学报（英文版）)

年 卷 期：2009年第6卷第3期

页      面：298-305页

核心收录：

学科分类：08[工学] 080203[工学-机械设计及理论] 0802[工学-机械工程] 

基　　金：supported in part by the Natural Science Foundation of China (NSFC) (Grant No:50875240) 

主　　题：defect detection scale-space Gausslan multi-scale representahon principal component analysis multivariate image anaIysis 

摘      要：Inspired by the coarse-to-fine visual perception process of human vision system,a new approach based on Gaussian multi-scale space for defect detection of industrial products was *** selecting different scale parameters of the Gaussian kernel,the multi-scale representation of the original image data could be obtained and used to constitute the multi- variate image,in which each channel could represent a perceptual observation of the original image from different *** Multivariate Image Analysis (MIA) techniques were used to extract defect features *** MIA combined Principal Component Analysis (PCA) to obtain the principal component scores of the multivariate test *** Q-statistic image, derived from the residuals after the extraction of the first principal component score and noise,could be used to efficiently reveal the surface defects with an appropriate threshold value decided by training *** results show that the proposed method performs better than the gray histogram-based *** has less sensitivity to the inhomogeneous of illumination,and has more robustness and reliability of defect detection with lower pseudo reject rate.