Improved Handwriting Recognition by Combining Two Forms of Hidden Markov Models and a Recurrent Neural Network

  • Authors:

  • Volkmar Frinken;Tim Peter;Andreas Fischer;Horst Bunke;Trinh-Minh-Tri Do;Thierry Artieres

  • Affiliations:

  • Institute of Computer Science and Applied Mathematics, University of Bern, Bern, Switzerland CH-3012;Institute of Computer Science and Applied Mathematics, University of Bern, Bern, Switzerland CH-3012;Institute of Computer Science and Applied Mathematics, University of Bern, Bern, Switzerland CH-3012;Institute of Computer Science and Applied Mathematics, University of Bern, Bern, Switzerland CH-3012;LIP6 - Université Pierre et Marie Curie, Paris, France 75016;LIP6 - Université Pierre et Marie Curie, Paris, France 75016

  • Venue:
  • CAIP '09 Proceedings of the 13th International Conference on Computer Analysis of Images and Patterns
  • Year:
  • 2009

Quantified Score

Hi-index 0.00

Visualization

Abstract

Handwritten word recognition has received a substantial amount of attention in the past. Neural Networks as well as discriminatively trained Maximum Margin Hidden Markov Models have emerged as cutting-edge alternatives to the commonly used Hidden Markov Models. In this paper, we analyze the combination of these classifiers with respect to their potential for improving recognition performance. It is shown that a significant improvement can in fact be achieved, although the individual recognizers are highly optimized state-of-the-art systems. Also, it is demonstrated that the diversity of the recognizers has a profound impact on the improvement that can be achieved by the combination.