Text Localisation and Handwriting Recognition: Application to Numeral Extraction and Recognition

This report discusses several general aspects of text localisation and handwriting recognition. In particular, we consider their applications to extraction and recognition of numerals written on Giro forms. For text localisation, we investigate the problem of extracting text printed or written inside boxes on forms. We review a number of representative methods for solving this problem, describe the implementation of one of them, and present some experimental results obtained on real data. For handwriting recognition, we rst present the standard general methodology, then apply it to handwritten numeral recognition, and nally propose a new approach, called perturbationbased, that allowed us to boost the recognition rate up to 99:1% on a worldwide standard database. CR