Character context: a shape descriptor for Arabic handwriting recognition

Abstract. In the handwriting recognition field, designing good descriptors are substantial to obtain rich information of the data. However, the handwriting recognition research of a good descriptor is still an open issue due to unlimited variation in human handwriting. We introduce a “character context descriptor” that efficiently dealt with the structural characteristics of Arabic handwritten characters. First, the character image is smoothed and normalized, then the character context descriptor of 32 feature bins is built based on the proposed “distance function.” Finally, a multilayer perceptron with regularization is used as a classifier. On experimentation with a handwritten Arabic characters database, the proposed method achieved a state-of-the-art performance with recognition rate equal to 98.93% and 99.06% for the 66 and 24 classes, respectively.

[1]  Yao Bi.  Challenges and Solutions of Chinese Cultural Terms in Interpretation , 2015 .

[2]  Sabri A. Mahmoud,et al.  Arabic Handwritten Alphanumeric Character Recognition using Fuzzy Attributed Turning Functions , 2011 .

[3]  Mohamed Ali Mahjoub,et al.  Multiple models of Bayesian networks applied to offline recognition of Arabic handwritten city names , 2013, ArXiv.

[4]  Sargur N. Srihari,et al.  An Assessment of Arabic Handwriting Recognition Technology , 2012 .

[5]  Guojun Lu,et al.  Review of shape representation and description techniques , 2004, Pattern Recognit..

[6]  Nicolai Petkov,et al.  Distance sets for shape filters and shape recognition , 2003, IEEE Trans. Image Process..

[7]  Ahmed Bouridane,et al.  HACDB: Handwritten Arabic characters database for automatic character recognition , 2013, European Workshop on Visual Information Processing (EUVIP).

[8]  Sabri A. Mahmoud,et al.  Recognition : A Survey , 2013 .

[9]  Monji Kherallah,et al.  Towards Unsupervised Learning for Arabic Handwritten Recognition Using Deep Architectures , 2015, ICONIP.

[10]  Chafic Mokbel,et al.  Arabic handwriting recognition using baseline dependant features and hidden Markov modeling , 2005, Eighth International Conference on Document Analysis and Recognition (ICDAR'05).

[11]  Sagi Eppel.  Tracing the boundaries of materials in transparent vessels using computer vision , 2015, ArXiv.

[12]  Abdurazzag Ali Aburas,et al.  Arabic handwriting recognition: Challenges and solutions , 2008, 2008 International Symposium on Information Technology.

[13]  Ivan Nunes da Silva,et al.  Multilayer Perceptron Networks , 2017 .

[14]  A. Ben Hamza,et al.  Geodesic Object Representation and Recognition , 2003, DGCI.

[15]  Monji Kherallah,et al.  A New Design Based-SVM of the CNN Classifier Architecture with Dropout for Offline Arabic Handwritten Recognition , 2016, ICCS.

[16]  Gaurav Harit,et al.  An improved contour-based thinning method for character images , 2011, Pattern Recognit. Lett..

[17]  Monji Kherallah,et al.  An Improved Arabic Handwritten Recognition System using Deep Support Vector Machines , 2016, Int. J. Multim. Data Eng. Manag..

[18]  Pierre Soille,et al.  Morphological Image Analysis: Principles and Applications , 2003 .

[19]  Partha Bhowmick,et al.  Robust binarization of degraded documents using adaptive-cum-interpolative thresholding in a multi-scale framework , 2011, 2011 International Conference on Image Information Processing.

[20]  Jitendra Malik,et al.  Shape matching and object recognition using shape contexts , 2010, 2010 3rd International Conference on Computer Science and Information Technology.

[21]  Jinchang Ren,et al.  Knowledge-Based Baseline Detection and Optimal Thresholding for Words Segmentation in Efficient Pre-Processing of Handwritten Arabic Text , 2008, Fifth International Conference on Information Technology: New Generations (itng 2008).

[22]  Sergio Escalera,et al.  Blurred Shape Model for binary and grey-level symbol recognition , 2009, Pattern Recognit. Lett..