Share Email Print

Optical Engineering

Image segmentation to inspect 3-D object sizes
Author(s): Jui-Pin Hsu; Chiou-Shann Fuh
Format Member Price Non-Member Price
PDF $20.00 $25.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

Object size inspection is an important task and has various applications in computer vision. For example, the automatic control of stone-breaking machines, which perform better if the sizes of the stones to be broken can be predicted. An algorithm is proposed for image segmentation in size inspection for almost round stones with high or low texture. Although our experiments are focused on stones, the algorithm can be applied to other 3-D objects, We use one fixed camera and four light sources at four different positions one at a time, to take four images. Then we compute the image differences and binarize them to extract edges. We explain, step by step, the photographing, the edge extraction, the noise removal, and the edge gap filling. Experimental results are presented.

Paper Details

Date Published: 1 January 1996
PDF: 10 pages
Opt. Eng. 35(1) doi: 10.1117/1.600895
Published in: Optical Engineering Volume 35, Issue 1
Show Author Affiliations
Jui-Pin Hsu, National Taiwan Univ. (Taiwan)
Chiou-Shann Fuh, National Taiwan Univ. (Taiwan)

© SPIE. Terms of Use
Back to Top