Dot Detection of Braille Images Using A Mixture of Beta Distributions

Al-Saleh Al-Saleh

doi:10.3844/jcssp.2011.1749.1759

Abstract

Problem statement: Braille is a tactile format of written communication for people with low vision and blindness worldwide. Optical Braille Recognition (OBR) offers many benefits to Braille users and people who work with them. Approach: This study presents an algorithm for detecting dots composing braille characters in an image of embossed braille material obtained by an optical scanner. We assumed that a mixture of Beta distributions could model the histogram of a scanned braille document. The core of the proposed method was the use of stability of thresholding with Beta distribution to initiate the process of thresholds estimation. Segmented Braille image was used to form a grid that contains recto dots and another one that contains verso dots. Results: Braille dots composing characters on both singlesided and double-sided documents were automatically identified from those grids with excellent accuracy. Conclusion: The experiment showed that the proposed method obtained very good results but it requires more testing on different scanned Braille document images.

Highlights

Braille is a writing system that enables blind and partially sighted people to read and write through touch. It was invented by Louis Braille, a French teacher of the blind Information about Deaf Blindness
We found that using a commercially available flatbed scanner may certainly provide a better and cost-effective solution
One of the earliest and comprehensive approaches to use a flatbed scanner is that of Bunke and Spitz (2006)

Summary

INTRODUCTION

Braille is a writing system that enables blind and partially sighted people to read and write through touch. In addition to the non-standard setup and equipment, the images obtained frequently suffer from the many problems of camera-based image acquisition (e.g., aberrations, irregular lightness, relatively low resolution) (Antonacopoulos and Bridson, 2004). For this reason, we found that using a commercially available flatbed scanner may certainly provide a better and cost-effective solution. One of the earliest and comprehensive approaches to use a flatbed scanner is that of Bunke and Spitz (2006) Both singlesided and double-sided Braille documents are scanned at 100dpi with 16 gray levels produced. The rest of the study is organized as follows: material and methods, results, discussion and conclusion

MATERIALS AND METHODS

RESULTS

CONCLUSION