ICDAR2013 - Competition on Gender Prediction from Handwriting

Introduction

The prediction of gender from handwriting is a very interesting research field. It has many applications including the forensic application where it can help investigators focusing more on a certain category of suspects.
There are a few studies regarding the automatic detection of the gender of a handwritten document [1-3]. The aim of this competition is to attract the interest of the document analysis community to this research area and to measure the performance of recent advances in this field..

The aim of this competition is to attract the interest of the document analysis community to this research area and to measure the performance of recent advances in this field.

This competition is organized in the scope of the Twelfth International Conference on Document Analysis and Recognition ICDAR2013 that will be held in Washington, DC.

The data collection has been done in Qatar University by research assistant Wael Al-Ayoubi within a research project NPRP 09 – 864 – 1 – 128 founded by Qatar Foundation and lead by Dr. Somaya Al-Maadeed.

  

The competition is now online at Kaggle.

Data and Evaluation Procedure

The dataset that will be used in this study is a subset of the QUWI dataset presented in ICFHR2012 [4]. This dataset has more than 1000 writers of approximately 50% male and 50% female writers.

For participants who do not have an image-processing background, a set of geometric features extracted from all the images will be provided. Those features are described in [5]
The evaluation procedure will be the correct classification rate, ie. the percentage of documents correctly classified.

Important dates

March 5th: competition open.
April 15th: deadline for submissions.
April 30th: competition paper available.

Organizers

  • Dr. Abdelâali Hassaïne received the “Ingénieur d’Etat” degree in computer science from “Université de Tlemcen”, Algeria in 2005, the “Master recherche” degree in imaging and computer graphics from “INSA de Lyon”, France, in 2006, and the Ph.D. degree in mathematical morphology from “Mines ParisTech”, France, in 2009. From January to July 2010, he worked as a postdoctoral fellowship on the identification and authentication of paintings and artworks in “Université de Saint-Etienne”, France. In January 2011, he joined Qatar University as a postdoctoral fellowship on document management and writer identification. His research interests are in mathematical morphology, feature extraction and document image processing.
  • Dr. Somaya Al-Ma’adeed received her BSc in Computer Science from Qatar University- Qatar in 1994, she received her MSc in Mathematics and Computer Science from Alexandria University-Egypt in 1999, and her PhD in Computer Science from Nottingham University in 2004. Following her BSc, she worked in academia (Qatar University), where she did research in the areas of character recognition, writer identification, speech recognition, tendering systems and document management. She has published around 20 papers in the above general areas. Dr. Somaya is now working as an assistant professor in Computer Science and Engineering department at Qatar University.
  • Prof. Ali Mohamed Jaoua is a faculty member of computer Science and engineering department, University of Qatar. He obtained the degree of “Docteur es-Science” (1987) in computer science, from the University Paul Sabatier of Toulouse (France), “Doctor Engineer” (1979) from Institute Polytechnic of Toulouse, and “Engineer in Computer Science” from ENSEEIHT of Toulouse (1977). He has also initially been selected to study in the higher school of Mathematics and Physics, in Lycee hoche (Versailles, from 1971-1974), and got also a degree from Orsay (Paris Sud) University in 1973 in Mathematics, and Physics. His research areas are Software and Information Engineering, Text Mining, Knowledge Engineering, Program Fault Tolerance, conceptual reasoning, search engine, information retrieval and document structuring. He has been working on the Use of Relational Methods in Computer Science since 1984, and the application of formal concept analysis in Information Engineering since 1990.
  • Prof. Jihad Mohamad Alja’am received his Ph.D in Computer Sciences and Mathematics of Computing, Southern University – National Council for Scientific Research – CNRS UNIT 816, 1994, an M.S. Computer Science (Soft Computing, Algorithms, Logic, and Artificial Intelligence), Southern University and INRIA-Toulouse 1990 and a B.Sc. Computer Science (Soft Computing, Algorithms, Logic, and Artificial Intelligence), Southern University, 1989. Dr. Alja’am is a Professor in the Computer Science and Engineering Department at Qatar University. He teaches many courses in computing starting from basics to advanced like: Programming Concepts, Advanced Programming, Design and Analysis of Algorithms, Compiler, Graph Theory and Artificial intelligence. His research interests includes: Soft Computing, Combinatorics, Intelligent Algorithms and Optimization, Data Mining and Natural Langauge Processing. Dr. Alja’am has rich experiences in IT projects management and consultancy services (IBM, RTS, INRIA) as well as in IT training and community services (i.e., Office Automation). Dr. Alja’am is co-author of 12 IT books and has over 70 journal and conference publications. He participated in different scientific international conferences. Dr. Alja’am is involved in different research projects funded by Qatar Foundation and Qatar University. He is a regular reviewer for the ACM Computing Reviews


References

[1] Bandi, K., Srihari, S.N., Writer demographic identification using bagging and boosting. In: Proc. International Graphonomics Society Con- ference (IGS). pp. 133–137 (2005).

[2] Liwicki, M., Schlapbach, A., Loretan, P., Bunke, H., Automatic detection of gender and handedness from online handwriting. In: Proc. 13th Conference of the International Graphonomics Society. pp. 179–183 (2007).

[3] Liwicki, M., Schlapbach, A., Bunke, H., Automatic gender detection using on-line and off-line information. Pattern Analysis and Applications 14, 87–92 (2011).

[4] Al-Ma’adeed, S., Ayouby, W., Hassaine, A., Aljaam, J., QUWI: An Arabic and English Handwriting Dataset for Offline Writer Identification. In: Frontiers in Handwriting Recognition, International Conference on. Bari, Italy (September 2012).

[5] Hassaïne, A., Al-Maadeed, S. and Bouridane, A., A Set of Geometrical Features for Writer Identification. Neural Information Processing. Springer Berlin/Heidelberg, 2012..

© 2016 Qatar University
Hosted by Qatar University