A CONNECTIONIST SYSTEM FOR LEARNING AND RECOGNITION OF STRUCTURES - APPLICATION TO HANDWRITTEN CHARACTERS

A connectionist system for learning and recognition of structures is d eveloped. The system is a cascade of two different modules, one for de tecting linear structures (primitives) and the other for integrating t hese linear structures. A connectionist model implementing Hough trans form has been used for the first module. The peaks in the Hough space are found by iterative verification method. A multilayered perceptron (four layers) with suitably chosen number of nodes and links has been used for the second module. As long as the size of the output layer of first module remains fixed (even if the size of input image changes), the same second module can be used and this is because the modules op erate independently. The system performance is tested on handwritten B engali character set.