Handwritten mathematical formula recognition using a statistical approach

We present a probabilistic framework for a mathematical expression recognition system. The system is flexible in that its grammar can be extended easily, thanks to its graph grammar which eliminates the need for specifying rule precedence. It is also optimal in the sense that all possible interpretations of the expressions are expanded, without making early commitments or hard decisions. The current system is able to recognize shorter expressions well and in real time. In this paper, we give an overview of the whole system and describe in detail our context sensitive graph grammar and the parsing process.