Since the late 1960s a lot of research has been done in the field of parsing mathematical formulae, for a range of purposes from the recognition of a person's scribings with a pen and tablet, through to the automatic interpretation and efficient storage of printed tables of integrals that have been scanned from books. Whatever the purpose, there are a number of approaches that can be used. Some are more suited to typeset while others are more suited to handwritten input.
The main difference between handwritten and typeset input is that typeset input has, at least for a single source, a much more rigorous and predictable nature with regard to its layout and appearance. Handwriting, on the other hand, exhibits a great deal of variability, even for a single author. There are unpredictable variations in the size of symbols, layout, and notational conventions used, which even vary within a single formula. When dealing with handwritten input, it is important to be able to interpret formulae reliably, in spite of minor disturbances in the positions and sizes of symbols.
A good source of general information on formula recognition is ``General Diagram Recognition Methodologies'' by Blostein , and Chapter 22 of ``Handbook of Character Recognition and Document Image Analysis'', by Blostein and Grbavec .
This chapter will discuss existing formula entry methods: command line interfaces, template-style editors, and graphical pen and tablet entry systems. For each of these, their strengths and weaknesses are discussed. This chapter then discusses issues in formula recognition that apply to both handwritten and typeset input. Existing formula parsing systems are then presented, with attention paid to their ability to process handwritten input.
.
This chapter will discuss existing formula entry methods: command line interfaces, template-style editors, and graphical pen and tablet entry systems. For each of these, their strengths and weaknesses are discussed. This chapter then discusses issues in formula recognition that apply to both handwritten and typeset input. Existing formula parsing systems are then presented, with attention paid to their ability to process handwritten input.