Mathematical learning from digital libraries and the web is a challenging problem for people with visual impairments and blindness. In this paper, we focus on developing the mathematical learning skills of braille users with a new assistive technology developed to retrieve semantically mathematical information from the web. This kind of research is still in the study phase. This paper presents an overview of assistive technologies for braille users followed by a description of the proposed system, which works in four phases. In the first phase, we translate a query math formula in braille into MathML code, and then we extract the structural and semantic meaning from the MathML expressions using multilevel presentation. In the classification phase, we choose a multilevel similarity measure based on K-Nearest Neighbors to evaluate the relevance between expressions. Finally, the query result is converted to braille math expressions. Experiments based on our database show that the new system provides more efficient results in responding to user queries.

Handwriting Arabic character recognition is one of the most challenging and complex tasks of research in Optical Character Recognition (OCR) and little research has been achieved in this area in the past few decades. This is due to the cursive nature of Arabic writing and the lack of public Arabic handwriting databases. In this paper, we present a general model of OCR system and an overview on several recently researches on offline handwriting Arabic character recognition systems. To evaluate the performance of these systems we compare their results using same database Benchmarking IFN/ENIT.

No abstract

Abstract-Math search or mathematical expression retrieval has become a challenging task. Mathematical expressions are very complex, they are highly symbolic, and they have a semantic meaning that we should respect. In this paper, we propose a similarity search method for mathematical expression based on a multilevel representation of expressions and a multilevel search. We used the K-Nearest Neighbors with three types of distances to evaluate relevance between expressions. In the experimental level, the proposed system significantly outperforms statistical algorithms.