Handwriting recognition using local methods for normalization and global methods for recognition

a major problem in handwriting recognition is the huge variability and distortions of patterns. Elastic models based on local observations and dynamic programming such HMM are efficient to absorb this variability. But their vision is local. Furthermore global models such Neural Network having a fixed input size are efficient to make correlations on an entire pattern. But then cannot face to length variability, and they are very sensitive to distortions. This paper proposes to use the power of these two classes of models. The elastic model is used to normalize the input image and the fixed model performs the recognition. The elastic model used is an NSHP-HMM and the global model used is a SVM. The NSHP-HMM searchs the important features and absorbs the distortions. According to the localisation of these features a pattern can be normalized to a standard size. Then the S V M is used to estimate global correlations and classify the pattern. The first results are encouraging and tend to confirm the validity of our approach.