Lexicon reduction using dots for off-line Farsi/Arabic handwritten word recognition

Authors:
Saeed Mozaffari;Karim Faez;Volker Märgner;Haikal El-Abed
Affiliations:
Pattern Recognition and Image Processing Laboratory, Electrical Engineering Department, Amirkabir University of Technology, Tehran 15914, Iran;Pattern Recognition and Image Processing Laboratory, Electrical Engineering Department, Amirkabir University of Technology, Tehran 15914, Iran;Institute of Communications Technology (IFN), Technical University of Braunschweig, Braunschweig 38092, Germany;Institute of Communications Technology (IFN), Technical University of Braunschweig, Braunschweig 38092, Germany
Venue:
Pattern Recognition Letters
Year:
2008

Citing 15
Cited 9

Techniques for automatically correcting words in text

ACM Computing Surveys (CSUR)
Handwritten Word Recognition Using Segmentation-Free Hidden Markov Modeling and Segmentation-Based Dynamic Programming Techniques

IEEE Transactions on Pattern Analysis and Machine Intelligence
A technique for computer detection and correction of spelling errors

Communications of the ACM
A new segmentation technique for omnifont Farsi text

Pattern Recognition Letters
Unconstrained Farsi handwritten word recognition using fuzzy vector quantization and hidden Markov models

Pattern Recognition Letters
Lexicon Reduction in an HMM-Framework Based on Quantized Feature Vectors

ICDAR '97 Proceedings of the 4th International Conference on Document Analysis and Recognition
Serial classifier combination for handwritten word recognition

ICDAR '95 Proceedings of the Third International Conference on Document Analysis and Recognition (Volume 2) - Volume 2
Handwritten Sentence Recognition

ICPR '00 Proceedings of the International Conference on Pattern Recognition - Volume 3
Recognising handwritten Arabic manuscripts using a single hidden Markov model

Pattern Recognition Letters
Lexical Post-Processing Optimization for Handwritten Word Recognition

ICDAR '03 Proceedings of the Seventh International Conference on Document Analysis and Recognition - Volume 1
Recognition of hand-printed characters based on structural description and inductive logic programming

Pattern Recognition Letters
Arabic Handwriting Recognition Competition

ICDAR '05 Proceedings of the Eighth International Conference on Document Analysis and Recognition
Pre-processing Methods for Handwritten Arabic Documents

ICDAR '05 Proceedings of the Eighth International Conference on Document Analysis and Recognition
Offline Arabic Handwriting Recognition: A Survey

IEEE Transactions on Pattern Analysis and Machine Intelligence
Variable duration hidden Markov model and morphological segmentation for handwritten word recognition

IEEE Transactions on Image Processing

Zero knowledge hidden Markov model inference

Pattern Recognition Letters
Font-based Persian character recognition using simplified fuzzy ARTMAP neural network improved by fuzzy sets and particle swarm optimization

CEC'09 Proceedings of the Eleventh conference on Congress on Evolutionary Computation
Binary segmentation with neural validation for cursive handwriting recognition

IJCNN'09 Proceedings of the 2009 international joint conference on Neural Networks
A neuro-fuzzy inference engine for Farsi numeral characters recognition

Expert Systems with Applications: An International Journal
Binary segmentation algorithm for English cursive handwriting recognition

Pattern Recognition
W-TSV: Weighted topological signature vector for lexicon reduction in handwritten Arabic documents

Pattern Recognition
Arabic handwriting recognition using structural and syntactic pattern attributes

Pattern Recognition
Offline arabic handwritten text recognition: A Survey

ACM Computing Surveys (CSUR)
Effect of delayed strokes on the recognition of online Farsi handwriting

Pattern Recognition Letters

Quantified Score

Hi-index	0.10

Visualization

Abstract

Unlike many other languages, 18 out of 32 Farsi characters have dots appearing in groups of one, two or three. Some of these letters share common primary shapes, differing only in the number of dots and whether the dots are above or below the primary shape. In this paper, a new concept of using dots in a cursively handwritten Farsi/Arabic word is introduced for lexicon reduction and a fast method for extracting dots is presented. The technique involves extraction and representation of number and position of dots from off-line handwritten words to eliminate unlikely candidates. Experimental results on a set of 12,000 handwritten word images yield a lexicon reduction of 93% with accuracy of 85%. The proposed lexicon reduction algorithm achieves the speedup factor of 2 as well as 13% improvement in recognition rate.