A Deep HMM model for multiple keywords spotting in handwritten documents

Simon Thomas (1, 2) , Clement Chatelain (1, 2) , Laurent Heutte (1, 2) , Thierry Paquet (1, 2) , Yousri Kessentini (1)

1 LITIS - Laboratoire d'Informatique, de Traitement de l'Information et des Systèmes
2 DocApp - LITIS - Equipe Apprentissage

In this paper, we propose a query by string word spotting system able to extract arbitrary key-words in handwritten documents, taking both segmen-tation and recognition decisions at the line level. The system relies on the combination of a HMM line model made of keyword and non-keyword (filler) models, with a deep neural network (DNN) that estimates the state-dependent observation probabilities. Experiments are carried out on RIMES database, an unconstrained hand-written document database that is used for benchmark-ing different handwriting recognition tasks. The ob-tained results show the superiority of the proposed frame-work over the classical GMM-HMM and standard HMM hybrid architectures.

Mots clés: DNN HMM; Handwriting Recognition; Keyword Spotting; Hidden Markov Models; Hybrid Deep architecture; Deep neural network

Domaines: Traitement du texte et du document

Simon Thomas, Clement Chatelain, Laurent Heutte, Thierry Paquet, Yousri Kessentini. A Deep HMM model for multiple keywords spotting in handwritten documents. Pattern Analysis and Applications, 2015, 18 (4), pp.1003-1015. ⟨hal-01089151⟩