1 January 1996 Image segmentation to inspect 3-D object sizes
Author Affiliations +
Optical Engineering, 35(1), (1996). doi:10.1117/1.600895
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.
Jui-Pin Hsu, Chiou-Shann Fuh, "Image segmentation to inspect 3-D object sizes," Optical Engineering 35(1), (1 January 1996). http://dx.doi.org/10.1117/1.600895

Image segmentation

Light sources



Image processing

3D image processing

Edge detection

Back to Top