Automatic detection of gender and handedness from on-line handwriting
Marcus Liwicki, Andreas Schlapbach, Peter Loretan, Horst Bunke · BORIS (University Library Bern) · 2007
Abstract. In this paper we address the problem of classifying handwritten data with respect to gender and handedness. For the classification we apply state-of-the-art classification methods to distinguish between male and female handwriting, and left- and right- handedness. Two classification systems have been evaluated, the first being based on Support Vector Machines and the second being based on Gaussian Mixture Models. Both systems show an improved performance over human-based classification. 1.