Gender Prediction from Handwriting

We employ one of the challenges of The Twelfth International Conference on Document Analysis and Recognition (ICDAR 2013). Predict if a handwritten document has been produced by a male or a female writer. The detail can be found at http://handwriting. qu.edu.qa/icdar-2013-competitions/ gender-prediction/. Besides being an interesting research topic of its own, automatically identifying subcategories can be used to improve a handwriting recognition system. The variability within a certain category is smaller than within a complete population, which allows us to train specialized recognizers. Another application is demographic studies. A concrete example would be to study the handwriting available on the worldwide web and to find out how many people from each category contributed to the data. It also has many applications including the forensic application where it can help investigators focusing more on a certain category of suspects. The purpose of this work is to apply several classification methods to the handwritten dataset.