Please use this identifier to cite or link to this item:
|Title:||Combining slanted-frame classifiers for improved HMM-based Arabic handwriting recognition||Authors:||Hajj Mohamad, Ramy Al
|Affiliations:||Department of Electrical Engineering||Keywords:||Arabic handwriting
Hidden Markov models
|Issue Date:||2009||Part of:||IEEE transactions on pattern analysis and machine intelligence||Volume:||31||Issue:||7||Start page:||1165||End page:||1177||Abstract:||
The problem addressed in this study is the offline recognition of handwritten Arabic city names. The names are assumed to belong to a fixed lexicon of about 1,000 entries. A state-of-the-art classical right-left hidden Markov model (HMM)-based recognizer (reference system) using the sliding window approach is developed. The feature set includes both baseline-independent and baseline-dependent features. The analysis of the errors made by the recognizer shows that the inclination, overlap, and shifted positions of diacritical marks are major sources of errors. In this paper, we propose coping with these problems. Our approach relies on the combination of three homogeneous HMM-based classifiers. All classifiers have the same topology as the reference system and differ only in the orientation of the sliding window. We compare three combination schemes of these classifiers at the decision level. Our reported results on the benchmark IFN/ENIT database of Arabic Tunisian city names give a recognition rate higher than 90 percent accuracy and demonstrate the superiority of the neural network-based combination. Our results also show that the combination of classifiers performs better than a single classifier dealing with slant-corrected images and that the approach is robust for a wide range of orientation angles.
|URI:||https://scholarhub.balamand.edu.lb/handle/uob/1756||Open URL:||Link to full text||Type:||Journal Article|
|Appears in Collections:||Department of Electrical Engineering|
Show full item record
checked on May 6, 2021
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.