Recognition of Amharic Braille Using Direction Field

No Thumbnail Available

Date

2011-06

Journal Title

Journal ISSN

Volume Title

Publisher

Addis Ababa University

Abstract

Invented by Louis Braille in 1829, braille has been a widely used means of written communication for the blind people around the world. Since its introduction in Ethiopia, there have been piles of Amharic braille documents produced by the blind people for different purposes. Since these documents are usually read and understood only by the same group of people, the blind, who have written them, the invaluable knowledge and information found there is highly restricted from reaching the sighted society. Automatic recognition of braille documents is therefore very instrumental in bridging the communication gab that exists between the blind and the sighted people. This thesis presents an approach for recognition of Amharic braille documents. We have used direction field tensor, which uses Gaussian filters and derivatives of Gaussians, for noise removal and isolation of braille dots from their background. We also designed a new skewness correction technique, which exploits the horizontal direction nature of braille dots. Attempts are made to determine braille dot sizes automatically so that the system works for different braille dot sizes. Braille character lines are constructed in order for subsequent operations to be performed only on the character lines. A half character detection method, which differentiates braille dots from noises is applied. Having recognized the half characters through analysis of their dot positions, the braille cells are formulated by way of examining horizontal distances between the half characters. We have finally used a lookup table for translating each of the formulated braille cells into their corresponding Amharic print characters. Braille documents, especially those that were used by previous works for comparison, are collected for experiment purpose. Our system achieved an average accuracy of 98.5%. 99.9% accuracy is achieved for good quality braille documents, while the accuracy for poor quality braille documents is 96.5%. The small errors observed in the experiment are attributed to some stains and defects present on braille documents.

Description

Keywords

Braille Using; Direction Field

Citation

Collections