Neural Networks for Lampung Characters Handwritten Recognition

Abstract

Character recognition technique associates a symbolic identity with the image of a character. Different characters and languages have different structures and features. Lampung character and language are different with any other languages. We have developed Lampung handwritten character recognition using back-propagation neural networks. However since some Lampung characters have similar features, hierarchical network system was performed to optimize the training and recognition algorithm. The experiment results give reasonable results of the recognition rate for the training set. 86.5% of basic characters and more than 97% for characters with tone marks can be recognized.