Off line cursive word recognition with a hybrid neural-HMM system

Abstract : In a recent publication [1], we have introduced a neural predictive system for on-line word recognition. Our approach implements a Hidden Markov Model (HMM)-based cooperation of several predictive neural networks. The task of the HMM is to guide the training procedure of neural networks on successive parts of a word. Each word is modeled by the concatenation of letter-models corresponding to the letters composing it. Successive parts of a word are this way modeled by different neural networks. A dynamical segmentation allows to adjust letter-models to the great variability of handwriting encountered in the words. Our system combines Multilayer Neural Networks and Dynamic Programming with an underlying Left-Right Hidden Markov Model (HMM). In this paper, we present an extension of this model to off-line word recognition. We use on-line data in these off-line experiments, generating a binary image from trajectory data. The feature extraction module then turns each binary image into a sequence of feature vectors, called ‘frames’, combining low-level and high-level features in a new feature extraction paradigm. Some results for word recognition are presented.
Document type :
Conference papers
Complete list of metadatas
Contributor : Lip6 Publications <>
Submitted on : Wednesday, October 25, 2017 - 5:35:44 PM
Last modification on : Thursday, March 21, 2019 - 12:59:46 PM

Links full text



Zsolt Wimmer, Sonia Garcia-Salicetti, Bernadette Dorizzi, Patrick Gallinari. Off line cursive word recognition with a hybrid neural-HMM system. BSDIA'97 - First Brazilian Symposium on Advances in Document Image Analysis, Nov 1997, Curitiba, Brazil. pp.249-260, ⟨10.1007/3-540-63791-5_19⟩. ⟨hal-01623879⟩



Record views