Graph Similarity Features for HMM-Based Handwriting Recognition in Historical Documents

Authors:
Andreas Fischer;Kaspar Riesen;Horst Bunke
Affiliations:
-;-;-
Venue:
ICFHR '10 Proceedings of the 2010 12th International Conference on Frontiers in Handwriting Recognition
Year:
2010

Citing 0
Cited 2

Lexicon-free handwritten word spotting using character HMMs

Pattern Recognition Letters
W-TSV: Weighted topological signature vector for lexicon reduction in handwritten Arabic documents

Pattern Recognition

Quantified Score

Hi-index	0.00

Visualization

Abstract

Automatic transcription of historical documents is vital for the creation of digital libraries. In this paper we propose graph similarity features as a novel descriptor for handwriting recognition in historical documents based on Hidden Markov Models. Using a structural graph-based representation of text images, a sequence of graph similarity features is extracted by means of dissimilarity embedding with respect to a set of character prototypes. On the medieval Parzival data set it is demonstrated that the proposed structural descriptor significantly outperforms two well-known statistical reference descriptors for single word recognition.