Handwriting recognition is such a complex classification problem that it is quite usual now to make co-operate several classification methods at the preprocessing stage or at the classification stage. In this paper, we present an original two stages recognizer. The first stage is a model-based classifier that stores an exhaustive set of character models. The second stage is a discriminative classifier that separates the most ambiguous pairs of classes. This hybrid architecture is based on the idea that the correct class almost systematically belongs to the two more relevant classes found by the first classifier. Experiments on Unipen database show a 30% improvement on a 62 classes recognition problem.

No abstract

The multiplication of handheld devices using the pen (electronic book, tablet PC, PDA, smart phone. . . ) as a way of interaction, require an efficient recognition system in order to substitute both keyboard and mouse.In this paper, we present a new writer-independent system dedicated to the automatic recognition of on-line texts. (geometrical and lexical) in order to provide the best transcription of the input signal. This system uses a very large French lexicon (200 000 words) which covers a vast field of application. This recognition process is based on the activationverification model proposed in perceptive psychology. A set of experts encodes the input signal and extract probabilistic informations at several levels of abstraction (geometrical and morphological). A neural expert generates a tree of segmentation hypotheses. This tree is explored by a probabilistic fusion expert that uses all the available informations

We present in this contribution a new system dedicated to the analysis of hand-printed dynamic text. I t appears as an alternative to merchandized personal digital assistants (PDAs) which are very user restricting and automatic cursive word recognizers that have been developed in laboratories and have still not reached a marketable target in spite of their accuracy. The whole treatment process, from the acquisition to the eficient reading, is integrated in a user-friendly interface. The results on an omni-writer text database are very encouraging. They should be improved nition to the write,: by using a new lexicon driven expert that adapts the recog-

We have recently developed in our lab a text recognizer for on-line texts written on a touch-terminal. We present in this paper several strategies to adapt this recognizer in a self-supervised way to a given writer and compare them to the supervised adaptation scheme. The baseline system is based on the activationverification cognitive model. We have designed this recognizer to be writer-independent but it may be adapted to be writer-dependent in order to increase the recognition speed and rate. The classification expert can be iteratively modified in order to learn the particularities of a writer. The best self-supervised adaptation strategy is called prototype dynamic management and gets good results, close to those of the supervised methods. The combination of supervised and self-supervised strategies increases accuracy again. Results, presented on a large database of 90 texts (5,400 words) written by 38 different writers are very encouraging with an error rate lower than 10 %.