Access Restriction

Author Kumar, G. ♦ Govindaraju, V.
Source IEEE Xplore Digital Library
Content type Text
Publisher Institute of Electrical and Electronics Engineers, Inc. (IEEE)
File Format PDF
Copyright Year ©2014
Language English
Subject Domain (in DDC) Technology ♦ Engineering & allied operations ♦ Other branches of engineering
Subject Keyword Hidden Markov models ♦ Bayes methods ♦ Feature extraction ♦ Logistics ♦ Image segmentation ♦ Image recognition ♦ Approximation methods ♦ Bayesian Active Learning ♦ Spotting ♦ Handwritten Multilingual Documents ♦ Script Independent
Abstract We propose a script independent Bayesian framework for keyword spotting in multilingual handwritten documents. The approach relies on local character level score and global word level hypothesis scores and learns a Bayesian logistic regression classifier to distinguish between keywords and non-keywords. In a Bayesian formulation of logistic regression, the integral over weights becomes intractable. Variational approximation is used for inference. In order to learn a robust classifier with minimal number of samples, we apply Bayesian active learning framework to request labels for those word images which provide maximum information gain in improving the classifier. We evaluate our system on multilingual datasets, publicly available IAM dataset for English, AMA for Arabic and LAW dataset for Devanagiri. The system is also evaluated on a synthetic multilingual dataset prepared by combining samples from IAM, AMA and LAW datasets. The results are comparable with the state of art multilingual keyword spotting framework.
Description Author affiliation: Dept. of Comput. Sci. & Eng., Univ. at Buffalo, Amherst, NY, USA (Kumar, G.; Govindaraju, V.)
ISBN 9781479943357
ISSN 21676445
Educational Role Student ♦ Teacher
Age Range above 22 year
Educational Use Research ♦ Reading
Education Level UG and PG
Learning Resource Type Article
Publisher Date 2014-09-01
Publisher Place Greece
Rights Holder Institute of Electrical and Electronics Engineers, Inc. (IEEE)
e-ISBN 9781479943340
Size (in Bytes) 454.63 kB
Page Count 6
Starting Page 357
Ending Page 362

Source: IEEE Xplore Digital Library