Knowledge-based image management system for object identification

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.<<ETX>>

[1]  N. Nandhakumar,et al.  The artificial intelligence approach to pattern recognition--a perspective and an overview , 1985, Pattern Recognit..

[2]  Martin D. Levine,et al.  Low Level Image Segmentation: An Expert System , 1984, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[3]  J. A. Fullwood,et al.  An approach to knowledge-driven segmentation , 1985, Image Vis. Comput..

[4]  Mark S. Fox,et al.  Constraint-Directed Search: A Case Study of Job-Shop Scheduling , 1987 .

[5]  Celestine A. Ntuen,et al.  An Approach To Object Knowledge Representation For Image Understanding Expert System Model , 1988, Twenty-Second Asilomar Conference on Signals, Systems and Computers.