DocumentCode :
1403543
Title :
Application of adaptive convolution masking to the automation of visual inspection
Author :
Skinner, David R. ; Benke, Kurt K. ; Chung, Michael J.
Author_Institution :
Defence Sci. & Technol. Organ., Ascot Vale, Vic., Australia
Volume :
6
Issue :
1
fYear :
1990
fDate :
2/1/1990 12:00:00 AM
Firstpage :
123
Lastpage :
127
Abstract :
An approach is presented for the automation of important aspects of human visual inspection in quality control. Pattern recognition and digital image processing are used to detect and classify defects in full gray-scale images of complex mechanical assemblies. The method simulates the processes of adaptation, fixation, and feature extraction in the human visual system. It applies an algorithm for optimizing convolution masks to distinguish between acceptable and unacceptable images. As a numerical example, the technique is used to detect a number of defects in X-ray images of complex mechanical assemblies
Keywords :
computer vision; inspection; mechanical engineering computing; quality control; X-ray images; adaptive convolution masking; complex mechanical assemblies; computer vision; digital image processing; feature extraction; fixation; full gray-scale images; pattern recognition; quality control; visual inspection; Assembly; Automation; Convolution; Digital images; Feature extraction; Gray-scale; Humans; Inspection; Pattern recognition; Quality control;
fLanguage :
English
Journal_Title :
Robotics and Automation, IEEE Transactions on
Publisher :
ieee
ISSN :
1042-296X
Type :
jour
DOI :
10.1109/70.88127
Filename :
88127
Link To Document :
بازگشت