A syllable based model for handwriting recognition

TL;DR

This paper presents a novel syllable-based model for handwriting recognition that improves handling out-of-vocabulary words by integrating syllabic n-gram models, evaluated on French and English datasets.

Contribution

Introduces a supervised syllabification method and integrates syllabic n-gram models into handwriting recognition, enhancing out-of-vocabulary word coverage.

Findings

Achieves competitive recognition performance on French RIMES and English IAM datasets.

Outperforms lexicon and character n-gram models in coverage and accuracy.

Effectively handles out-of-vocabulary words with limited syllable sets.

Abstract

In this paper, we introduce a new modeling approach of texts for handwriting recognition based on syllables. We propose a supervised syllabification approach for the French and English languages for building a vocabulary of syllables. Statistical n-gram language models of syllables are trained on French and English Wikipedia corpora. The handwriting recognition system, based on optical HMM context independent character models, performs a two pass decoding, integrating the proposed syllabic models. Evaluation is carried out on the French RIMES dataset and English IAM dataset by analyzing the performance for various coverage of the syllable models. We also compare the syllable models with lexicon and character n-gram models. The proposed approach reaches interesting performances thanks to its capacity to cover a large amount of out of vocabulary words working with a limited amount of syllables combined with statistical n-gram of reasonable order.