Call For Papers
Contact Us

  Applying Power Law on Texture Structure to Identify the Writing Style in Ancient Manuscripts  
  Authors : Ahmad Abd Al-Aziz; Mervat Gheith
  Cite as:


This work presents the preliminary results for identifying the ancient handwritten writing styles in Arabic manuscripts. The aim of this work is to discriminate between different writing styles appear in different dated ancient Arabic manuscripts in three Islamic historical ages (Contemporary, Ottoman and Mamluk) with objective to evaluate the capability of applying Zipf law on texture structures extracted by Spatial Gray Level dependency (SGLD) method, our approach relies on applying SGLD on handwritten ancient text image to extract the texture structures then applying Zipf’s distribution on document image texture structure. Based on this method we extract a feature presents the document image structure distribution and evaluate its efficiency for writing style identification.


Published In : IJCSN Journal Volume 3, Issue 4

Date of Publication : August 2014

Pages : 220 - 224

Figures : 06

Tables : --

Publication Link : Applying Power Law on Texture Structure to Identify the Writing Style in Ancient Manuscripts




Ahmad Abd Al-Aziz : received his M.SC., in computer science from Institute of Statistical Studies and Researches (ISSR), Cairo University, he enrolled in PhD in computer science in (ISSR), Cairo University. He joined Canadian International College (CIC), in 2007 as assistant lecturer. His main areas of research interest are Pattern Recognition, Social Network analysis, Big data, Natural Language processing, sentiment analysis. He had multiple disciplines background: social sciences (since he gained his PhD in behavior sciences from Ain Shams University) and computer science empowered him to scale out his research areas in several topics related to applying information theories in social sciences. Ahmad published two scientific papers in image analysis and pattern recognition.

Mervat Gheith : is assistant professor at Institute of Statistical Studies and Researches (ISSR), Cairo University, her main research interests are artificial intelligence, pattern recognition, image processing and natural language processing. Mervat published several scientific papers in fields of natural language processing and artificial intelligence.








Writing Style Identification

Spatial Gray Level Dependency

Power Law

Texture Analysis

This work has been done with objective to discriminate between different writing styles in different Islamic historical ages: Contemporary, Ottoman and Mamluk. We aimed to extend the approach of applying Zipf’’s law in image applications by proposed a new approach based on texture structures generated by SGLM method to identify the writing styles in ancient Arabic manuscripts. This method has an advantage of analyzing the structure of document image patterns instead of image quantization limitations. By applying Zipf’s law on generated SGLD we compute the area under Zipf curve for each writing style and evaluate the experimental results. These results show that applying this method is efficient in identifying different writing styles in different historical Arabic manuscripts. The main disadvantage is that the processing time of SGLD is high in addition the query and stored writing style image should be processed in the same orientation in SGLD matrix generation. In our future work we plan to add more features e.g. curve slope with area under curve which is evaluated in this work in order to increase the efficiency of writing style identification task.










[1] F. Aiolli and M.Giollo, “A Study on the writer identification task for paleographic document analysis”, Proceedings of the 11th IASTED International conference on artificial intelligence and applications (AIA), 2011.

[2] L.Schomaker, G. Abbink and S. Selen, “Writer and writing-style classification in the recognition of online handwriting”, in: Proceedings of the European workshop on handwriting analysis and recognition: A European perspective, pp. 12-13. 1994.

[3] E. Vellingiriraj and P. Balasubramanie, “Recognition of ancient tamil handwritten Characters in palm manuscripts using genetic algorithm. International journal of scientific engineering and technology,vol. 2, pp. 342-346, 2013.

[4] R. Pareti and N. Vincent, “Global method based on pattern occurrences for writer identification”, 10th International workshop on frontiers in handwriting recognition, 2006.

[5] C. Djeddi, L. Souici-Meslati and , A. Ennaji, “Writer recognition on arabic handwritten documents”, in: Proceedings of the 5th international conference on Image and Signal Processing, pp. 493-501, 2012.

[6] R. Herzog, A. Solth and B. Neumann, “Using Harris Corners for the retrieval of graphs in historical manuscripts”, 12th International conference on document analysis and recognition, 2013.

[7] J. Brenard, Digital Image Processing, Springer-Verlag Berlin, Germany, 2005.

[8] V. Eglin, F. Lebourgeois, S. Bres, H. Emptoz, Y. Leydier, I. Moalla, and F. Drira, “Computer assistance for digital libraries: contributions to middle-ages and authors manuscripts exploitation and enrichment”. 2nd International conference on document image analysis for libraries (DIAL'06), pp. 265-280, 2006.

[9] A. Al-Aziz, M. Gheith and A. Sayed, “Recognition for old Arabic manuscripts using spatial gray level dependence (SGLD)”, Egyptian Informatics Journal, vol. 12, pp. 37–43, 2011.

[10] Y. Caron, P. Makris and N. Vincent, “Use of power law models in detecting region of interest”, Pattern recognition, vol. 40, pp. 2521 – 2529, 2007.

[11] N. Vincent, P. Makris and J. Brodier, “Compressed image quality and Zipf’s law, in: Proceedings of international conference on signal processing (ICSPIFIC- IAPRWCC2000), pp. 1077–1084, 2000.

[12] Y. Caron, P. Makris, N. Vincent, “A method for detecting artificial objects in natural environments”, in: Proceedings of international conference on pattern recognition (ICPR2002-IAPR), pp. 600–603, 2002.

[13] L. Lakhdar and H. Merouani, “A novel technique of steganalysis in uncompressed image through zipf’s law”, International journal of computer applications, vol. 40, 2012.

[14] M. Roomi and S. Saranya, “Bayesian classification of fabrics using binary co-occurrence matrix. International journal of information sciences and techniques (IJIST) ,vol. 2, 2012.

[15] W. Boussellaa, H. El-Abed and A. Zahour, “A concept for the separation of foreground/background in arabic historical manuscripts using hybrid methods”, 7th International symposium on virtual reality, archaeology and cultural heritage VAST, 2006.

[16] M. Sharma, M. Markou, and S. Singh, “Evaluation of texture methods for image analysis”, in: Proceedings of the 7th Australian and New Zealand intelligent information systems conference, pp. 117–121, 2001.

[17] J. Eakins, “Content base image retrieval – can we make it deliver?”, 2nd UK Conference on image retrieval, 1999.

[18] K. Melessanaki, V. Papadakis, C. Balas and D. Anglos, “Laser induced breakdown spectroscopy and hyperspectral imaging analysis of pigments on an illuminated manuscript”, Spectrochimica Acta Part B 56, pp. 2337-2346, 2001.

[19] L.M. Al-Zoubeidy, and H. F. Al-Najar, “Arabic writer identification for handwriting images”. In: Procceeding of International Arab Conference on Information Technology, pp. 111-117, 2005.

[20] I. Moalla, M. Alimi, F. Lebourgeois, and H. Emptoz, “Image analysis for palaeography inspection, 2nd International conference on document image analysis for libraries (DIAL’06), pp. 303–311, 2006.

[21] M. S.Azmi, K. Omar, M. F. Nasrudin, A. K. Muda, A. Abdullah and K. Ghazali, “Features extraction of arabic calligraphy using extended triangle model for digital jawi paleography analysis”, International journal of computer information systems and industrial management applications, vol. 5, pp. 696-703, 2013.

[22] H. Said, T. Tan and K. Baker, "Personal identification based on handwriting", Journal of pattern recognition society, Vol. 33, pp. 149-160, 2000.