Abstract:
The Braille system has been used by the visually impaired for writing and reading. According to limited availability of the Braille text books an efficient usage of the books becomes a very important. This paper considers a problem to convert a scanned Braille document to text. The Braille cells are segmented. And the dots from each cell is extracted and converted in to a number sequence. These are mapped to the suitable alphabets of the language. The Braille cell has a standard representation but the mapping differs for each language. In this paper mapping of English, and Russian are considered.
We use the method of comparison to the prototype. In the process of recognition of Braille in the preparatory phase we determine the completeness of a group of cells on the basis of which we obtain data about the width and height of the group. And knowing the distance between the groups, we analyze the results of Braille detection.
In this paper the algorithm that formed the basis for creating optical character recognition program was compiled. Six-point recognition software Braille for Russian and English characters was developed and was tested. Our application provides the ability to customize the grid on the document. In the result we can increase the number of recognized characters.
Keywords:Braille, pattern recognition, computer modeling, system of signs for blind people, blind people.