Abstract
A prototype model of a knowledge-based image management system (KIMS), consisting of an image processing system and an expert system, was developed to demonstrate the feasibility of the automated inspection of a target object from X-ray images. It is shown that if the procedural knowledge and the declarative knowledge are known, rules can be developed which will be used to identify a target object from X-ray images. The authors report results for the various image analysis states of preprocessing, segmentation, feature extraction, understanding, and interpretation in KIMS with particular application to a regional representation scheme.
Original language | English |
---|---|
Pages (from-to) | 965-970 |
Number of pages | 6 |
Journal | Conference Proceedings - IEEE SOUTHEASTCON |
Volume | 3 |
Publication status | Published - 1989 |
Event | Proceedings - Energy and Information Technologies in the Southeast - Columbia, SC, USA Duration: 1989 Apr 9 → 1989 Apr 12 |
All Science Journal Classification (ASJC) codes
- Electrical and Electronic Engineering