Database-Driven Mathematical Character Recognition

摘要

We present an approach for recognising mathematical texts using an extensive LATEX 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 LATEX symbol, and reassembling the text by putting the appropriate LATEX commands at their corresponding positions of the original text inside a LATEX 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.