6 October 1998 Unsupervised image segmentation with the self-organizing map and statistical methods
Author Affiliations +
Abstract
In this paper a special type of image segmentation, a two- class segmentation, is considered. Defect detection in quality control applications is a typical two-class problem. The main idea in this paper is to train the two-class classifier with fault-free samples that is an unexpected approach. The reason is that defects are rare and expensive. The proposed defect detection is based on the following idea: an unknown sample is classified as a defect if it differs enough from the estimated prototypes of fault-free samples. The self-organizing map is used to estimate these prototypes. Surface images are used to demonstrate the proposed image segmentation procedure.
© (1998) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Jukka Iivarinen, Jukka Iivarinen, Ari J. E. Visa, Ari J. E. Visa, } "Unsupervised image segmentation with the self-organizing map and statistical methods", Proc. SPIE 3522, Intelligent Robots and Computer Vision XVII: Algorithms, Techniques, and Active Vision, (6 October 1998); doi: 10.1117/12.325796; https://doi.org/10.1117/12.325796
PROCEEDINGS
11 PAGES


SHARE
Back to Top