A new approach for the identification of writers of important ancient documents

In this paper, a novel approach is introduced for identifying the writer of a document, with special emphasis to paleography. Towards this direction, a mathematical quantity called plane curvature is introduced and a number of associated propositions are stated. Proper similarity measures of two curves are defined and a subsequent statistical analysis is applied. The efficiency of the method has been, first, tested on a public reference database. The methodology has also been applied to the very important problem of classifying 23 Byzantine codices and 46 Ancient inscriptions to their writers, thus achieving correct dating of their content. The inscriptions have been attributed to ten individual hands and the Byzantine codices to four writers. Prominent epigraphologists and classicists fully agree with the obtained classification.

[1]  Guillermo Sapiro,et al.  A Continuum Mechanical Approach to Geodesics in Shape Space , 2011, International Journal of Computer Vision.

[2]  Nikos Paragios,et al.  Shape registration in implicit spaces using information theory and free form deformations , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.

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

[4]  Yuan Yan Tang,et al.  A novel method for offline handwriting-based writer identification , 2005, Eighth International Conference on Document Analysis and Recognition (ICDAR'05).

[5]  Graham Leedham,et al.  Extraction and analysis of forensic document examiner features used for writer identification , 2007, Pattern Recognit..

[6]  Sabri A. Mahmoud,et al.  WRITER IDENTIFICATION OF ARABIC TEXT USING STATISTICAL AND STRUCTURAL FEATURES , 2013, Cybern. Syst..

[7]  Horst Bunke,et al.  A writer identification and verification system using HMM based recognizers , 2006, Pattern Analysis and Applications.

[8]  Joulia Chapran,et al.  Biometric Writer Identification: Feature Analysis and Classification , 2006, Int. J. Pattern Recognit. Artif. Intell..

[9]  J. B. Alonso,et al.  Writer identification based on graphology techniques , 2008, 2008 42nd Annual IEEE International Carnahan Conference on Security Technology.

[10]  Sharada Laxman Kore,et al.  The current state of art: handwriting a behavioral biometric for person identification and verification , 2012, ICACCI '12.

[11]  Nicholas R. Howe,et al.  Style-based retrieval for ancient Syriac manuscripts , 2011, HIP '11.

[12]  Pascal Frossard,et al.  Minimum Distance between Pattern Transformation Manifolds: Algorithm and Applications , 2009, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[13]  Bhabatosh Chanda,et al.  Writer Identification for Handwritten Telugu Documents Using Directional Morphological Features , 2010, 2010 12th International Conference on Frontiers in Handwriting Recognition.

[14]  Zhenyu He,et al.  Writer identification of Chinese handwriting documents using hidden Markov tree model , 2008, Pattern Recognit..

[15]  Chang-Dong Wang,et al.  A Stroke Shape and Structure Based Approach for Off-line Chinese Handwriting Identification , 2011 .

[16]  Sargur N. Srihari,et al.  Individuality of handwritten characters , 2003, Seventh International Conference on Document Analysis and Recognition, 2003. Proceedings..

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

[18]  Lior Wolf,et al.  Identifying Join Candidates in the Cairo Genizah , 2011, International Journal of Computer Vision.

[19]  Michael I. Miller,et al.  Large Deformation Diffeomorphic Metric Curve Mapping , 2008, International Journal of Computer Vision.

[20]  Xiuwen Liu,et al.  Shape of Elastic Strings in Euclidean Space , 2008, International Journal of Computer Vision.

[21]  Thierry Paquet,et al.  A writer identification and verification system , 2005, Pattern Recognit. Lett..

[22]  Lambert Schomaker,et al.  Using codebooks of fragmented connected-component contours in forensic and historic writer identification , 2007, Pattern Recognit. Lett..

[23]  Aleix M. Martínez,et al.  Rotation Invariant Kernels and Their Application to Shape Analysis , 2009, IEEE Transactions on Pattern Analysis and Machine Intelligence.