{"id":13218,"date":"2014-10-15T11:55:00","date_gmt":"2014-10-15T20:55:00","guid":{"rendered":"http:\/\/handwritinguniversity.com\/members\/?p=13218"},"modified":"2014-10-15T11:57:30","modified_gmt":"2014-10-15T20:57:30","slug":"can-a-computer-spot-female-handwriting-correctly","status":"publish","type":"post","link":"https:\/\/handwritinguniversity.com\/members\/weekly-newsletters\/can-a-computer-spot-female-handwriting-correctly\/","title":{"rendered":"Can a computer spot female handwriting correctly?"},"content":{"rendered":"

Predict if a handwritten document has been produced by a male or a female writer<\/p>\n

The prediction of gender from handwriting is a very interesting research field.<\/strong><\/h2>\n

It has many applications including the forensic application where it can help investigators focusing more on a certain category of suspects.\u00a0 But, is it accurate?<\/p>\n

\"gender1predictions\"<\/p>\n

There are a few studies regarding the automatic detection of the gender of a handwritten document\u00a0[1-3].<\/p>\n

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.<\/p>\n

The dataset used in this study has been described in this paper [4].<\/p>\n

A total of 475 writers produced 4 handwritten documents:<\/p>\n

the first page contains an Arabic handwritten\u00a0text which varies from one writer to another.
\nthe second page\u00a0contains an Arabic handwritten\u00a0text which is the same for all the writers.
\nthe third page contains an English handwritten\u00a0text which varies from one writer to another.
\nand the fourth\u00a0page\u00a0contains an English handwritten\u00a0text which is the same for all the writers.
\nThe training set consists of the first 282 writers for which the genders are provided.<\/p>\n

Participants are asked to predict the gender of the remaining 193 writers.<\/p>\n

For participants who are not familiar with digital image-processing, a set of features extracted from all the images will be provided. Those features are similiar to that of the previous 2011 and 2012 Arabic Writer Identification Contests. Those features are described in [5].<\/p>\n

 <\/p>\n

\n

------------ Special Newsletter Reader Offer ------------\r\n\r\n\"\"<\/a>\r\n
\r\nVisit the discount page now.<\/b><\/p>\n

<\/p>\n<\/div>\n

This competition is organized in the scope of the Twelfth\u00a0International Conference on Document Analysis and Recognition ICDAR2013\u00a0that will be held in Washington, DC.<\/p>\n

[1] Bandi, K., Srihari, S.N.,\u00a0Writer demographic identification using bagging and boosting. In: Proc. International Graphonomics Society Con- ference (IGS). pp. 133\u2013137 (2005).<\/p>\n

[2] Liwicki, M., Schlapbach, A., Loretan, P., Bunke, H.,\u00a0Automatic detection of gender and handedness from online handwriting. In: Proc. 13th Conference of the International Graphonomics Society. pp. 179\u2013183 (2007).<\/p>\n

[3] Liwicki, M., Schlapbach, A., Bunke, H.,\u00a0Automatic gender detection using on-line and off-line information. Pattern Analysis and Applications 14, 87\u201392 (2011).<\/p>\n

[4] Al-Ma\u2019adeed, S., Ayouby, W., Hassaine, A., Aljaam, J.,\u00a0QUWI: An Arabic and English Handwriting Dataset for Offline Writer Identification. In: Frontiers in Handwriting Recognition, International Conference on. Bari, Italy (September 2012).<\/p>\n

[5] Hassa\u00efne, A., Al-Maadeed, S. and Bouridane, A.,\u00a0A Set of Geometrical Features for Writer Identification. Neural Information Processing. Springer Berlin\/Heidelberg, 2012<\/p>\n

 <\/p>\n

Introducing…<\/h2>\n

\"\"<\/a><\/h2>\n

An interactive training program, marketing system, combined with a community of professional handwriting experts, speakers, authors, coaches, consultants, trainers, and full and part-time entrepreneurs. This is your invitation to join us.<\/p>\n

We Are Now Taking Enrollments for
\nCharter Members.<\/a><\/span><\/strong><\/p>\n

 <\/p>\n

\"calendar\"<\/p>\n