A Fast Lexically Constrained Viterbi Algorithm for On-line Handwriting Recognition

Alain Lifchitz (1) , Frederic Maire (2)

1 APA - Apprentissage et Acquisition des connaissances
2 School of Computing Science, Queensland University of Technology

Most on­line cursive handwriting recognition systems use a lexical constraint to help improve the recognition performance. Traditionally, the vocabulary lexicon is stored in a trie (automaton whose underlying graph is a tree). In this paper, we propose a solution based on a more compact data structure, the directed acyclic word graph (DAWG). We show that our solution is equivalent to the traditional system. Moreover, we propose a number of heuristics to reduce the size of the DAWG and present experimental results demonstrating a significant improvement.

Mots clés: Handwriting Recognition; compact DAWG; Large Vocabularies; HMM

Domaines: Intelligence artificielle [cs.AI]; Algorithme et structure de données [cs.DS]; Apprentissage [cs.LG]

Alain Lifchitz, Frederic Maire. A Fast Lexically Constrained Viterbi Algorithm for On-line Handwriting Recognition. Seventh International Wokshop on Frontiers in Handwriting Recognition - IWFHR-7, 2000, Amsterdam, Netherlands. pp.313-322. ⟨hal-00012559⟩