Knowledge based parallel recognition of handwritten alphanumerics

A novel knowledge-based parallel processing system has been designed for recognition of handwritten characters. With five quadtree-linked microprocessors, this system can extract features from the character image in four directions simultaneously. Through repetitive order-giving and information-gathering between the master and the slaves, the system can process the information at two levels: global and local. Simulation results show that the system greatly outperforms its serial processing version. >