Combining Statistical and Structural Approaches for Arabic Handwriting Recognition

A novel technique to recognize full range of shapes of Arabic handwritten characters is presented. This is done by combining statistical and structural approaches for character recognition. The statistical method first recognizes the main body of a character using modified direction features and Support Vector Machines. Then in structural classification, dot-descriptors are used to recognize the exact shape of an Arabic character. On IfN/ENIT benchmarking database, we achieved 96.71% accuracy for character main-bodies and 94.52% accuracy on the complete characters. Our results compare favorably with the state of the art.

[1]  Jason Weston,et al.  Fast Kernel Classifiers with Online and Active Learning , 2005, J. Mach. Learn. Res..

[2]  Ayoub Al-Hamadi,et al.  Arabic handwriting recognition using Gabor wavelet transform and SVM , 2012, 2012 IEEE 11th International Conference on Signal Processing.

[3]  Marc Schoenauer,et al.  An artificial immune system for offline isolated handwritten arabic character recognition , 2018, Evol. Syst..

[4]  Alireza Alaei,et al.  A Comparative Study of Persian/Arabic Handwritten Character Recognition , 2012, 2012 International Conference on Frontiers in Handwriting Recognition.

[5]  Mohamed Batouche,et al.  Investigation on deep learning for off-line handwritten Arabic character recognition , 2017, Cognitive Systems Research.

[6]  Nicole Vincent,et al.  Shape-Based Alphabet for Off-line Arabic Handwriting Recognition , 2007 .

[7]  Gernot A. Fink,et al.  Multi-stage HMM based Arabic text recognition with rescoring , 2015, 2015 13th International Conference on Document Analysis and Recognition (ICDAR).

[8]  Karbhari V. Kale,et al.  Zernike moment feature extraction for handwritten Devanagari compound character recognition , 2013, 2013 Science and Information Conference.

[9]  Hazem M. El-Bakry,et al.  Arabic Handwritten Characters Recognition Using Convolutional Neural Network , 2017 .

[10]  Bidyut Baran Chaudhuri,et al.  Offline recognition of handwritten Bangla characters: an efficient two-stage approach , 2012, Pattern Analysis and Applications.

[11]  Raed Abu Zitar,et al.  Development of an efficient neural-based segmentation technique for Arabic handwriting recognition , 2010, Pattern Recognit..

[12]  Umapada Pal,et al.  Off-line handwritten Thai name recognition for student identification in an automated assessment system , 2014, 2014 International Joint Conference on Neural Networks (IJCNN).

[13]  M. Bedda,et al.  Handwritten Arabic character recognition based on SVM Classifier , 2008, 2008 3rd International Conference on Information and Communication Technologies: From Theory to Applications.

[14]  Gernot A. Fink,et al.  Improvements in Sub-character HMM Model Based Arabic Text Recognition , 2014, 2014 14th International Conference on Frontiers in Handwriting Recognition.

[15]  Chih-Jen Lin,et al.  LIBSVM: A library for support vector machines , 2011, TIST.

[16]  Alireza Alaei,et al.  A New Two-Stage Scheme for the Recognition of Persian Handwritten Characters , 2010, 2010 12th International Conference on Frontiers in Handwriting Recognition.

[17]  Mohammad Alshayeb,et al.  KHATT: An open Arabic offline handwritten text database , 2014, Pattern Recognit..

[18]  Brijesh Verma,et al.  An investigation of the modified direction feature for cursive character recognition , 2007, Pattern Recognit..

[19]  Venu Govindaraju,et al.  Offline Arabic handwriting recognition: a survey , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.