Optical Braille character recognition with Support-Vector Machine classifier

Abstract

This paper introduces a system that uses Support-Vector Machine (SVM) to recognize Braille characters from an image. Braille images is captured by the digital cameras, and pre-process the Braille images, segment the Braille images by the image processing technology and then extract the Braille features by the fixed nature of Braille. The SVM system architecture is designed, and the specific image processing approach is introduced in detail in this paper. This method is simple, convenient, and easy to operate, also able to extract dots online in real time. The experiments show that the method is effective and accurate for Braille extraction.