N-Gram Language Model to Predict the Word Sequence in a Degraded Braille Document

Abstract

This paper presents a feature extraction method for optical Braille recognition (OBR) system to locate, extract and convert the Braille cells in one sided Indian language Braille documents. The Braille cells are located by implementing a grid-box designed using physical properties of a Braille cell. A Braille document image is a compilation of group of six dots. The physical position of each dot and its relevance with other neighboring dots in a single cell gives various Braille characters. After the grid-box is mapped with the Braille cells in the document, the mesh characters are extracted and are then mapped with existing database to translate them in required text. Mapping of Braille cells with mesh box and separation of characters and words from a Braille document was a challenging task. The unwanted dots or degraded dots way result in incorrect mapping of characters. In this paper we have used N-gram Language Models to Predict the word Sequence in case of wrong mapping of characters in extraction and conversion of the Braille cells.