Wang, Ching-Cheng (Professor of industrial engineering)
M.S. (Master of Science)
Department of Industrial Engineering
Engineering inspection; Quality control--Optical methods
Automated Visual Inspection (AVI) has wide quality control applications. When applying the machine vision for mensuration, AVI requires that the vision camera is mounted vertically to the surface of the inspection table. A misalignment makes the acquired visual information dependent of the inspected unit’s position. No inspected unit is placed without positioning errors. Thus, the normal alignment between vision camera and inspection table needs to be verified in order for the risk of unreliable results to be reduced. In this thesis, the unique verification method which checks the required normal alignment is explored and implemented. The normality is verified using the image of a standard reference square collected by the to-be-verified vision camera. The image of a square is a parallelogram if and only if the vision camera is normal to the inspection table. Hence, the parallelism hypotheses are tested to verify the normal alignment. Sensitivity analysis discloses the desirable experimental settings. In addition, field experiments are also carried out. In addition to the normal alignment, the scale factor, the conversion ratio of the scanned image to the acquired image, is needed for mensuration. Once the normal alignment is verified, the scale factor can be identified accurately at negligible cost using the scale calibration method explored in this thesis.
Chuang, Siang C., "Normality verfication and scale factor identification for automated visual inspection" (1991). Graduate Research Theses & Dissertations. 4136.
viii, 108 pages
Northern Illinois University
Rights Statement 2
NIU theses are protected by copyright. They may be viewed from Huskie Commons for any purpose, but reproduction or distribution in any format is prohibited without the written permission of the authors.
Includes bibliographical references (pages -69).