Title :
A knowledge-based image understanding environment for document processing
Author :
Li, Ying ; Lalonde, Marc ; Reiher, Eric ; Rizand, Jean-Francçois ; Zhu, Chong J.
Author_Institution :
CRIM, Montreal, Que., Canada
Abstract :
The CRIM Image Mining Environment (CIME) is an image understanding environment integrated with knowledge engineering technologies. The image understanding technology developed for CIME supports recognition tasks such as symbol recognition, contour line recognition, and general image processing operations. CIME is composed of an Object Model Description Language (OMDL) which allows for the semantic description of knowledge about objects and their context, an inference engine which performs image understanding based on the model descriptions in OMDL to achieve the recognition of complex objects, and a task builder which allows for the acquisition of image understanding knowledge and helps the application designer to build strategies for solving application problems through knowledge reuse
Keywords :
document image processing; edge detection; image recognition; inference mechanisms; knowledge acquisition; knowledge based systems; visual databases; CIME; CRIM Image Mining Environment; OMDL; Object Model Description Language; application problem solving; contour line recognition; document processing; image processing; inference engine; knowledge acquisition; knowledge engineering; knowledge reuse; knowledge-based image understanding; model descriptions; object recognition; semantic description; symbol recognition; task builder; Application software; Context modeling; Data mining; Educational institutions; Engines; Environmental management; Image processing; Image recognition; Knowledge management; Noise level;
Conference_Titel :
Document Analysis and Recognition, 1997., Proceedings of the Fourth International Conference on
Conference_Location :
Ulm
Print_ISBN :
0-8186-7898-4
DOI :
10.1109/ICDAR.1997.620656
