Online handwritten mathematical expression recognition

Official URL: http://risc01.sabanciuniv.edu/record=b1147833 (Table of Contents)

This thesis presents a system for online handwritten mathematical expression recognition that involves integrals, summation notation, superscripts and subscripts, square-roots, fractions, trigonometric and logarithmic functions; together with a user-interface for writing scientific article. The aim of this study is to utilize the most convenient man-machine-interface, a pen, for input of mathematical expressions. In pen-enabled devices, handwriting sequences are collected by the digitization of pen movements which outputs an array of coordinates called strokes. A neural network is trained for recognizing each stroke and a recursive algorithm parses the expression by combining neural network output and structure of the expression. The interface associated with the proposed system integrates the built-in recognition capabilities of the Microsoft's Tablet PC-API for recognizing textual input and also supports conversion of hand-drawn figures into PNG format, which enable the user to enter text, mathematics and draw figures in a single interface. After the recognition, all output is combined into one LATEX code and compiled into a PDF file.s The system presented in this thesis provides a natural interface, hence enables easyinput of mathematical expressions in all pen-enabled devices such as tablet PCs, PDAs, external tablet pads, electronic pen-boards etc.