Handwriting gender recognition system based on the one-class support vector machines

Abstract

Handwriting gender recognition becomes considerable matter for the document analysis community, due to its effective use in practical applications. This paper addresses the problem of classifying handwriting data with respect to gender. From the state of the art, only a few studies have been carried out in this field. Thus, we propose a new framework for classifying the gender from the handwriting document using the curvelet transform and a classification method based on One-Class Support Vector Machine (OC-SVM). In order to improve the robustness of the proposed system, multiple OC-SVM classifiers are combined according to the type of distance used into the kernel. Experimental results conducted on IAM datasets show the effective use of the OC-SVM for handwriting gender recognition comparatively to the state of the art.