Off-Line Text-Independent Arabic Writer Identification using Contour-Based Features

In this paper, we show how the combination and cooperation of six feature vectors computed from the minimum-perimeter polygon (MPP) contours of Arabic words can lead to very interesting results for off-line text-independent Arabic writer identification. These feature vectors are in the form of probability distribution functions (PDFs), and are based on the length, direction, angle and curvature measurements. First, the aforementioned features were extracted and tested separately using 82 writers from the IFN/ENIT database. Then, they were combined in different ways. Finally, the combination which led to the best identification rates was retained. Indeed, promising results were obtained using a set of common distance metrics and the Borda ranking algorithm for classification. More specifically, we obtained 90.2% identification rate for Top1, and 97.5% for Top10.

[1]  S. Gazzah,et al.  Arabic Handwriting Texture Analysis for Writer Identification Using the DWT-Lifting Scheme , 2007 .

[2]  Rachael D. Seidler,et al.  Differential effects of age on sequence learning and sensorimotor adaptation , 2006, Brain Research Bulletin.

[3]  Volker Märgner,et al.  Databases and Competitions: Strategies to Improve Arabic Recognition Systems , 2006, SACH.

[4]  Lambert Schomaker,et al.  Text-Independent Writer Identification and Verification Using Textural and Allographic Features , 2007, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[5]  Luiz Eduardo Soares de Oliveira,et al.  Author identification using writer-dependent and writer-independent strategies , 2008, SAC '08.

[6]  W. F. Clocksin,et al.  Structural Features of Cursive Arabic Script , 1999, BMVC.

[7]  Réjean Plamondon,et al.  Automatic signature verification and writer identification - the state of the art , 1989, Pattern Recognit..

[8]  Christian Viard-Gaudin,et al.  Automatic writer identification framework for online handwritten documents using character prototypes , 2009, Pattern Recognit..

[9]  Sargur N. Srihari,et al.  Automatic handwriting recognition and writer matching on anthrax-related handwritten mail , 2002, Proceedings Eighth International Workshop on Frontiers in Handwriting Recognition.

[10]  Chul E. Kim,et al.  Digital and cellular convexity , 1982, Pattern Recognit..

[11]  Rein van den Boomgaard,et al.  Methods for fast morphological image transforms using bitmapped binary images , 1992, CVGIP Graph. Model. Image Process..

[12]  Alicia Fornés,et al.  Writer Identification in Old Handwritten Music Scores , 2008, 2008 The Eighth IAPR International Workshop on Document Analysis Systems.

[13]  K. Ubul,et al.  Research on Uyghur off-line handwriting-based writer identification , 2008, 2008 9th International Conference on Signal Processing.

[14]  Jerzy Sas.  Handwriting Recognition Accuracy Improvement by Author Identification , 2006, ICAISC.

[15]  A. Rafiee,et al.  Off-Line Writer Recognition for Farsi Text , 2007, 2007 Sixth Mexican International Conference on Artificial Intelligence, Special Session (MICAI).

[16]  Ramesh Chaudhry,et al.  Identification of authorship using lateral palm print--a new concept. , 2004, Forensic science international.

[17]  Joseph N. Wilson,et al.  Handbook of computer vision algorithms in image algebra , 1996 .

[18]  G. P. van Galen,et al.  Error, stress and the role of neuromotor noise in space oriented behaviour. , 2000, Biological psychology.

[19]  Somaya Al-Máadeed,et al.  Writer identification using edge-based directional probability distribution features for arabic words , 2008, 2008 IEEE/ACS International Conference on Computer Systems and Applications.

[20]  Byung-Tae Chun,et al.  An effective method for combining multiple features of image retrieval , 1999, Proceedings of IEEE. IEEE Region 10 Conference. TENCON 99. 'Multimedia Technology for Asia-Pacific Information Infrastructure' (Cat. No.99CH37030).

[21]  Hanêne Ben-Abdallah,et al.  A novel approach for off-line Arabic writer identification based on stroke feature combination , 2009, 2009 24th International Symposium on Computer and Information Sciences.

[22]  Mohammad Rahmati,et al.  A New Method for Writer Identification and Verification Based on Farsi/Arabic Handwritten Texts , 2007 .

[23]  R Plamondon,et al.  Studying the variability of handwriting patterns using the Kinematic Theory. , 2009, Human movement science.

[24]  Ayman Al-Dmour,et al.  Arabic writer identification based on hybrid spectral–statistical measures , 2007, J. Exp. Theor. Artif. Intell..

[25]  Najoua Essoukri Ben Amara,et al.  Arabic Handwriting Texture Analysis for Writer Identification Using the DWT-Lifting Scheme , 2007, Ninth International Conference on Document Analysis and Recognition (ICDAR 2007).

[26]  R. Plamondon.  Looking at handwriting generation from a velocity control perspective. , 1993, Acta psychologica.

[27]  Lambert Schomaker,et al.  Advances in Writer Identification and Verification , 2007, Ninth International Conference on Document Analysis and Recognition (ICDAR 2007).

[28]  Tieniu Tan,et al.  Text-Independent Writer Identification Based on Fusion of Dynamic and Static Features , 2005, IWBRS.

[29]  Adel M. Alimi,et al.  Recovery of temporal information from off-line Arabic handwritten , 2005, The 3rd ACS/IEEE International Conference onComputer Systems and Applications, 2005..

[30]  F. Nadia,et al.  Personal Identification Based on Texture Analysis of Arabic Handwriting Text , 2006, 2006 2nd International Conference on Information & Communication Technologies.

[31]  Lambert Schomaker,et al.  Text-Independent Writer Identification and Verification on Offline Arabic Handwriting , 2007 .

[32]  Zhenyu He,et al.  Writer identification using global wavelet-based features , 2008, Neurocomputing.