Drawing Understanding System Incorporating Rule Generation Support with Man-Machine Interactions

Shin'ichi SATOH  Hiroshi MO  Masao SAKAUCHI  

IEICE TRANSACTIONS on Information and Systems   Vol.E77-D   No.7   pp.735-742
Publication Date: 1994/07/25
Online ISSN: 
Print ISSN: 0916-8532
Type of Manuscript: Special Section PAPER (Special Issue on Document Analysis and Recognition)
arawing understanding,  rule learning,  man-machine cooperation,  graphical user interface,  

Full Text: PDF>>
Buy this Article

The present study describes using the state transition type of drawing understanding framework to construct a multi-purpose drawing understanding system. This new system employs an understanding process that complies with the understanding rules, which are easily obtained by the user. The same set of user-provided rules must be used for the same type of target drawings, but for slightly different ones, fine tuning is required to obtain understanding rules. To overcome this inherent drawback in constructing drawing understanding systems, we extended the system using a newly constructed understanding rule generating support system. The resultant integrated system is based on a man-machine cooperation type interface, and can automatically generate rules from user-provided simple interactions using a graphical user interace (GUI). To obtain efficient rule generation, the system employs an inductive inference method as a learning algorithm. Map-drawing experiments were successfully carried out, and an evaluation based on a rule leaning error criterion subsequently revealed an efficient rule generation process.