2D Markovian modeling for character recognition and segmentation

Processing text components in multimedia contents remains a challenging issue for document indexing and retrieval. More specifically, handwritten characters processing is a very active field of pattern recognition. This paper describes an innovative two-dimensional approach for character recognition and segmentation. The method proposed combines Markovian modeling, efficient decoding algorithm together with a windowed spectral features extraction scheme. A rigorous evaluation methodology is achieved to analyse and discuss the performances obtained for digit and word recognition. Key-Words: Handwriting recognition, Markov Random fields, 2D dynamic programming.