Title :
Checking on the quality of gauge panel based on wavelet analysis
Author :
Liu, Shu-guang ; Liu, Ming-yuan ; He, Yue
Author_Institution :
Dept. of Machinery Eng., Xi´´an Inst. of Sci. & Technol., China
Abstract :
The wavelet transform has good local performance in both spatial and frequency domains. The two-dimensional discrete wavelet transform is a nearly ideal subband analysis/synthesis subsystem in image processing. Based on the fundamental theory of the wavelet transform, an edge detection method is successfully used in the feature extraction of a meter´s image. To obtain the pointing errors of meters on a gauge panel, a new machine vision inspection criterion for the assessment of pointing accuracy is proposed. On the basis of this research, a machine vision inspection system for automobile gauge panels is developed. It is used in an automobile assembly line, performing quality inspection tasks with high accuracy.
Keywords :
assembling; automatic optical inspection; automobile industry; computer vision; computerised numerical control; edge detection; feature extraction; quality control; wavelet transforms; automobile assembly line; automobile gauge panel quality checking; edge detection method; feature extraction; image processing; local performance; machine vision inspection criterion; pointing accuracy assessment; pointing errors; quality inspection task; subband analysis; two dimensional CNC system; two-dimensional discrete wavelet transform; wavelet analysis; Automobiles; Discrete wavelet transforms; Frequency domain analysis; Image analysis; Image edge detection; Image processing; Inspection; Machine vision; Wavelet analysis; Wavelet domain;
Conference_Titel :
Machine Learning and Cybernetics, 2002. Proceedings. 2002 International Conference on
Print_ISBN :
0-7803-7508-4
DOI :
10.1109/ICMLC.2002.1174483
