Classifying Patent Images

This report presents the work carried out for the image classification task in the course of the CLEF-IP 2011 competition. Based on the visual content, patent images are automatically classified into several drawing types, such as abstract drawings, tables, flow chart and graphs. For that purpose, a series of SVM classifiers, multi-modal fusion schemes and a variety of content-based low-level features for black and white images were used. The overall reported performance was promising. Our best runs achieved a true positive rate of over 66% and the reported average area under curve is over 0.9.