Giovanni Seni

Large vocabulary recognition of on-line handwritten cursive words

This paper presents a writer independent system for large vocabulary recognition of on-line handwritten cursive words. The system first uses a filtering module, based on simple letter features, to quickly reduce a large reference dictionary (lexicon) to a more manageable size; the reduced lexicon is subsequently fed to a recognition module. The recognition module uses a temporal representation of the input, instead of a static two-dimensional image, thereby preserving the sequential nature of the data and enabling the use of a Time-Delay Neural Network (TDNN); such networks have been previously successful in the continuous speech recognition domain. Explicit segmentation of the input words into characters is avoided by sequentially presenting the input word representation to the neural network-based recognizer. The outputs of the recognition module are collected and converted into a string of characters that is matched against the reduced lexicon using an extended Damerau-Levenshtein function. Trained on 2,443 unconstrained word images (11 k characters) from 55 writers and using a 21 k lexicon we reached a 97.9% and 82.4% top-5 word recognition rate on a writer-dependent and writer-independent test, respectively.

Non-cumulative character scoring in a forward search for online handwriting recognition

In this paper, we describe a novel and efficient search strategy as it is applied to on-line handwriting recognition. The recognition system, which is based on Viterbi decoding, computes posterior probabilities of characters based on sequences of observations, referred to as segments. Posterior distributions of segments are appealing because they allow correlation modeling of the entire segment. In addition, they provide a reliable confidence-rejection mechanism due to their discriminative nature. These posterior scores, which we term non-cumulative, cannot be used for hypothesis pruning as it is done in a standard time synchronous beam search. We propose an organization of the search algorithm that addresses the difficulties posed by the use of non-cumulative character scoring in an efficient way. We report on a writer-independent recognition system that achieves a tenfold reduction in the required number of theories while maintaining the same level of accuracy. Finally, we provide a comparison between the segmental posterior probabilities and the frame-based, class-conditional distributions of the traditional HMM approach that highlights the differences in the search methodology.

Online handwriting recognition in a form-filling task: evaluating the impact of context-awareness

Guiding a recognition task using a language model is commonly accepted as having a positive effect on accuracy and is routinely used in automated speech processing. This paper presents a quantitative study of the impact of the use of word models in online handwriting recognition applied to form-filling tasks on handheld devices. Two types of word models are considered: a dictionary, typically from few thousands and up to hundred-thousand words; and a grammar or regular expression generating a language several orders of magnitude bigger than the dictionary. It is reported that the improvement in accuracy obtained by the use of a grammar compares with the gain provided by the use of a dictionary. Finally, the impact of the word models on user acceptance of online handwriting recognition in a specific form-filling application is presented.