Balinese character recognition using bidirectional LSTM classifier

Abstract

The character recognition of cursive scripts always be provocative. The inherent challenges exists in cursive scripts captured researcher’s interest to crop up the issues that surface in building a reliable OCR. There exists many ancient languages that require state of the art techniques to be applied on them. Every such language has its own inherent complex structure. We proposed Balinese character recognition system by Recurrent Neural Network (RNN) approach, so that their characteristics may get substantial attention from research community. The Balinese has Brahmic Indic ancestor having cursive writing style nearest to Devangri, Sinhala and Tamil. We employed BLSTM networks on Balinese character recognition.