Database-driven mathematical character recognition

We present an approach for recognising mathematical texts using an extensive (LTEX)-T-A symbol database and a novel recognition algorithm. The process consists essentially of three steps: Recognising the individual characters in a mathematical text by relating them to glyphs in the database of symbols, analysing the recognised glyphs to determine the closest corresponding (LTEX)-T-A symbol, and reassembling the text by putting the appropriate (LTEX)-T-A commands at their corresponding positions of the original text inside a (LTEX)-T-A picture environment. The recogniser itself is based on a novel variation on the application of geometric moment invariants. The working system is implemented in Java.