Share Email Print
cover

Proceedings Paper

Offline handwritten word recognition using MQDF-HMMs
Author(s): Sitaram Ramachandrula; Mangesh Hambarde; Ajay Patial; Dushyant Sahoo; Shaivi Kochar
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

We propose an improved HMM formulation for offline handwriting recognition (HWR). The main contribution of this work is using modified quadratic discriminant function (MQDF) [1] within HMM framework. In an MQDF-HMM the state observation likelihood is calculated by a weighted combination of MQDF likelihoods of individual Gaussians of GMM (Gaussian Mixture Model). The quadratic discriminant function (QDF) of a multivariate Gaussian can be rewritten by avoiding the inverse of covariance matrix by using the Eigen values and Eigen vectors of it. The MQDF is derived from QDF by substituting few of badly estimated lower-most Eigen values by an appropriate constant. The estimation errors of non-dominant Eigen vectors and Eigen values of covariance matrix for which the training data is insufficient can be controlled by this approach. MQDF has been successfully shown to improve the character recognition performance [1]. The usage of MQDF in HMM improves the computation, storage and modeling power of HMM when there is limited training data. We have got encouraging results on offline handwritten character (NIST database) and word recognition in English using MQDF HMMs.

Paper Details

Date Published: 8 February 2015
PDF: 10 pages
Proc. SPIE 9402, Document Recognition and Retrieval XXII, 94020J (8 February 2015); doi: 10.1117/12.2076144
Show Author Affiliations
Sitaram Ramachandrula, Hewlett-Packard Labs. India (India)
Mangesh Hambarde, Hewlett-Packard Labs. India (India)
Ajay Patial, Hewlett-Packard Labs. India (India)
Dushyant Sahoo, Indian Institute of Technology Delhi (India)
Shaivi Kochar, Jamia Millia Islamia (India)


Published in SPIE Proceedings Vol. 9402:
Document Recognition and Retrieval XXII
Eric K. Ringger; Bart Lamiroy, Editor(s)

© SPIE. Terms of Use
Back to Top