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