Optimizing the number of states for HMM-based on-line handwritten whiteboard recognition

Jürgen Geiger, Joachim Schenk, Frank Wallhoff, Gerhard Rigoll

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

13 Scopus citations

Abstract

In this paper, we present a novel way to determine the number of states in Hidden-Markov-Models for on-line handwriting recognition. This method extends the Bakis length modeling method which has succesfully been applied to off-line handwriting recognition. We propose a modification to the Bakis method and present a technique to improve the topology with a small number of iterations. Furthermore, we investigate the influence of state tying. In an experimental section, we show that our improved system outperforms a system with Bakis length modeling by 1.5 % relative and with fixed length modeling by 5.1 % relative on the IAM-On-DB-t1 benchmark.

Original languageEnglish
Title of host publicationProceedings - 12th International Conference on Frontiers in Handwriting Recognition, ICFHR 2010
Pages107-112
Number of pages6
DOIs
StatePublished - 2010
Event12th International Conference on Frontiers in Handwriting Recognition, ICFHR 2010 - Kolkata, India
Duration: 16 Nov 201018 Nov 2010

Publication series

NameProceedings - 12th International Conference on Frontiers in Handwriting Recognition, ICFHR 2010

Conference

Conference12th International Conference on Frontiers in Handwriting Recognition, ICFHR 2010
Country/TerritoryIndia
CityKolkata
Period16/11/1018/11/10

Fingerprint

Dive into the research topics of 'Optimizing the number of states for HMM-based on-line handwritten whiteboard recognition'. Together they form a unique fingerprint.

Cite this