A generic 2D approach of handwriting recognition

In this paper, we present a two-dimensional approach of the processing of handwriting. It combines a Markovian model, an efficient decoding algorithm, a windowed spectral features extraction scheme and a rigorous evaluation methodology. We applied this principle to a digit recognition task and to a word recognition task.

• Type: Conference
• Year: 2005
• Where: ICDAR
• Authors: Sylvain Chevalier, Françoise J. Prêteux, Edouard Geoffrois, Melanie Lemaitre
• Keywords: Digit Recognition Task, Document Analysis, ICDAR 2005, Recognition Task, Word Recognition Task