Paper Info
Title
A comparison of discrete and continuous hidden Markov models for phrase spotting in text images
Abstract
In spotting for phrases in text images, speed and accuracy are important considerations. In a hidden Markov model (HMM) based spotter recognition time is dominated by the time required to compute the state conditional observation probabilities. These probabilities are a measure of how well the data match each state in the model. In this paper discrete and continuous hidden Markov models are compared based on speed and accuracy in spotting for phrases in text images. For the discrete HMM, vector quantization is used to associate each continuous feature vector with a discrete value. For the continuous HMMs, the observation distributions for the feature vectors are modeled by either a single Gaussian, or a mixture of two Gaussians. Comparisons were made on a subset of the UW English Document Image Database I. The best accuracy was observed when a mixture of two Gaussians was used in the continuous HMM. The discrete HMM provides for faster spotting particularly when long phrases are used.
Year
DOI
Venue
1995
10.1109/ICDAR.1995.599022
ICDAR-1
Keywords
Field
DocType
image recognition,speech recognition,robustness,hidden markov model,vector quantization,feature vectors,handwriting recognition,image segmentation,optical character recognition,hidden markov models,feature vector
Feature vector,Pattern recognition,Computer science,Optical character recognition,Handwriting recognition,Speech recognition,Image segmentation,Vector quantization,Gaussian,Artificial intelligence,Hidden Markov model,Spotting
Conference
ISBN
Citations 
PageRank 
0-8186-7128-9
8
0.71
References 
Authors
6
3
Name
Order
Citations
PageRank
Francine Chen11218153.96
L. D. Wilcox22910.32
Dan S. Bloomberg39816.94