Intelligent CAI system for artistic calligraphy evaluation by using neural-fuzzy reasoning

This study describes on-going project of the drawing understanding and evaluation framework to construct artistic calligraphy oriented CAI system for artistic education. This new CAI system employs an understanding process that complies with the understanding rules, which are easily obtained by the system and user. The rule set for evaluation and understanding the calligraphy that created by the user are compiled with the rule obtained by the system. However, fine tuning is required to establish effective evaluation and understanding rules. To establish the collaborative ICAI system, we extended the system using a newly constructed understanding rule generating support system. The resultant integrated system is based on man-machine cooperation type interface, and can automatically generate rules from user-provided simple interactions using a graphical user interface. To obtain efficient rule generation and learning strategy, the system employs the neural-fuzzy tuning as a learning scheme.