Hidden Markov Model Length Optimization for Handwriting Recognition Systems

Authors:
Matthias Zimmermann;Horst Bunke
Affiliations:
-;-
Venue:
IWFHR '02 Proceedings of the Eighth International Workshop on Frontiers in Handwriting Recognition (IWFHR'02)
Year:
2002

Citing 0
Cited 12

Parsing N-Best Lists of Handwritten Sentences

ICDAR '03 Proceedings of the Seventh International Conference on Document Analysis and Recognition - Volume 1
Optimizing the Number of States, Training Iterations and Gaussians in an HMM-based Handwritten Word Recognizer

ICDAR '03 Proceedings of the Seventh International Conference on Document Analysis and Recognition - Volume 1
Multiple Handwritten Text Line Recognition Systems Derived from Specific Integration of a Language Model

ICDAR '05 Proceedings of the Eighth International Conference on Document Analysis and Recognition
Character Duration Modeling for Speed Improvements in the BBN Byblos OCR System

ICDAR '05 Proceedings of the Eighth International Conference on Document Analysis and Recognition
Offline Grammar-Based Recognition of Handwritten Sentences

IEEE Transactions on Pattern Analysis and Machine Intelligence
An implicit segmentation-based method for recognition of handwritten strings of characters

Proceedings of the 2006 ACM symposium on Applied computing
Rejection strategies for offline handwritten text line recognition

Pattern Recognition Letters
Rejection strategies for offline handwritten text line recognition

Pattern Recognition Letters
Explicit length modelling for statistical machine translation

IbPRIA'11 Proceedings of the 5th Iberian conference on Pattern recognition and image analysis
Off-line cursive script recognition: current advances, comparisons and remaining problems

Artificial Intelligence Review
Explicit length modelling for statistical machine translation

Pattern Recognition
Rule-based trajectory segmentation for modeling hand motion trajectory

Pattern Recognition

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper investigates the use of three different schemes to optimize the number of states of linear left-to-right Hidden Markov Models (HMM). As the first method we describe the fixed length modeling scheme where each character model is assigned the same number of states. The second method considered is the Bakis length modeling where the number of model states is set to a given fraction of the average number of observations of the corresponding character. In the third length modeling scheme the number of model states is set to a specified quantile of the corresponding character length histogram. This method is called quantile length modeling. A comparison of the different length modeling schemes has been carried out with a handwriting recognition system using off-line images of cursively handwritten English words from the IAM database. For the fixed length modeling a recognition rate of 61% has beenachieved. Using Bakis or quantile length modeling the word recognition rates could be improved to over 69%.