Data sets for training, validation and testing are now available (Please click here)
Handwriting is one of the oldest and the most common modes of communication which has retained its importance despite the tremendous growth of digital documents. In addition to the traditional task of handwriting recognition, correlation is also known to exist between handwriting and the identity as well as different demographic attributes of the writer. The focus of this competition lies on three aspects, the identity, the gender and the handedness of writers. We propose the organization of a competition to recognize the identity, the gender as well as the handedness of an individual using offline digitized samples of his/her handwriting. This is the second competition of its series with the addition of the new task of handedness classification. The first competition was organized in conjunction with ICDAR2015 and received a very encouraging response.
Identification of writers from handwritten samples is a well-known behavioral biometric modality that finds applications in a variety of problem areas including forensic document analysis, authentication of documents and verification of the genuineness of historical manuscripts etc. Likewise, automatic analysis of handwriting to identify gender and handedness of its writer can serve to develop useful commercial, governmental and forensic applications where it can help investigators focusing on a certain category of suspects.
Writer identification, gender and handedness classification from handwriting have been active areas of research during the recent years and a number of recognition systems realizing promising results have been reported in the literature. Most of the research on these and related tasks, however, has been carried out on handwritten texts in a single script. It is a well-known fact that in most cultures, at least two languages are spoken and written by a significant proportion of the population. Having writing samples of same individuals in multiple scripts allows studying the interesting problem of multi-script handwriting analysis where writing patterns that are common across different scripts may be exploited to study problems like writer identification, gender classification and handedness detection.
In order to objectively compare the performance of recent advancements in writer identification, gender classification and handedness detection and to investigate the performance of traditional script-dependent systems in a multi-script environment, we propose to organize this edition of Multi-script Writer Demographic Identification Competition using "QUWI" Database, in conjunction with the 15th International Conference on Frontiers in Handwriting Recognition, ICFHR 2016. The underlying objective of organizing this competition is to study the interesting scenarios when training and test samples of an individual are in two different scripts. The competition will also provide researchers with the opportunity to compare their algorithms under same experimental settings and evaluation protocols and, study the performance evolution of traditional systems in a more challenging experimental setup. A report on the competition will be published in the proceedings of ICFHR 2016. The report will comprise description of the participating methods, the evaluation protocol and the final rankings of the participating algorithms. The results of the competition will also be presented in a dedicated session at ICFHR 2016.