95 articles 

inria-00104794, version 1

Novel Hybrid NN/HMM Modelling Techniques for On-line Handwriting Recognition

Joachim Schenk () 1, Gerhard Rigoll () 1

Tenth International Workshop on Frontiers in Handwriting Recognition (2006)

Abstract: In this work we propose two hybrid NN/HMM systems for handwriting recognition. The tied posterior model approximates the output probability density function of a Hidden Markov Model (HMM) with a neural net (NN). This allows a discriminative training of the model. The second system is the tandem approach: A NN is used as part of the feature extraction, and then a standard HMM apporach is applied. This adds more discrimination to the features. In an experimental section we compare the two proposed models with a baseline standard HMM system. We show that enhancing the feature vector has only a limited effect on the standard HMMs, but a significant influence to the hybrid systems. With an enhanced feature vector the two hybrid models highly outperform all baseline models. The tandem approach improves the recognition performance by 4.6% (52.9% rel. error reduction) absolute compared to the best baseline HMM.

  • 1:  Institute for Human-Machine Communication
  • Technische Universität München
  • Domain : Computer Science/Document and Text Processing
    Computer Science/Computer Vision and Pattern Recognition
  • Keywords : On-line handwriting recognition – HMM – NN – hybrid – tandem – tied posteriors
  • Comment : http://www.suvisoft.com
 
  • inria-00104794, version 1
  • oai:hal.inria.fr:inria-00104794
  • From: 
  • Submitted on: Monday, 9 October 2006 14:24:04
  • Updated on: Monday, 9 October 2006 14:34:57