Abstract

Visually impaired people, face many problems to communicate and to study electronical scientific documents especially those containing mathematics expressions. To provide solutions in this topic, we propose an assistive system to help blind people to categorize mathematical formulas from electronical documents. The system acts on four steps: first the translation of query math formula into Presentation MathML code, and then we extract the structural and semantic meaning from the MathML expressions. In the classification phase, we used a deep learning as Recurrent Neural Network algorithm to classify the category of the query mathematical expression. Finally, the query result that is the category of mathematical formula is transformed into Braille code. Experiments were done using an experimental dataset composed of 1120 math expressions.
