Conferences on Intelligent Computer Mathematics - Birmingham 2008
CICM '08

Doctoral Programme

Birmingham, UK, 29-31 July 2008

Noureddin Sadawi: Chemical Document Analysis Abstract

The aim of my research is to develop a system that can parse a scanned chemical document and reconstruct its contents into a computer readable format. The research is going to focus on exploiting the connection between mathematical formulae recognition and chemical document analysis by applying available formulae recognition techniques during plain text retrieval via standard OCR to analyse embedded and isolated chemical formulae. In addition I want to develop techniques based on formal grammars for NMR table reconstruction, molecule drawing recognition and recognition of tabular data.