Data-Fusion Techniques for Open-Set Recognition Problems

Most pattern classification techniques are focused on solving closed-set problems in which a classifier is trained with samples of all classes that may appear during the testing phase. In many situations, however, samples of unknown classes, i.e., whose classes did not have any example during the training stage, need to be properly handled during testing. This specific setup is referred to in the literature as open-set recognition. Open-set problems are harder as they might be ill-sampled, not sampled at all, or even undefined. Differently from existing literature, here we aim at solving open-set recognition problems combining different classifiers and features while, at the same time, taking care of unknown classes. Researchers have greatly benefited from combining different methods in order to achieve more robust and reliable classifiers in daring recognition conditions, but those solutions have often focused on closed-set setups. In this paper, we propose the integration of a newly designed open-set graph-based optimum-path forest (OSOPF) classifier with genetic programming (GP) and majority voting fusion techniques. While OSOPF takes care of learning decision boundaries more resilient to unknown classes and outliers, GP combines different problem features to discover appropriate similarity functions and allows a more robust classification through early fusion. Finally, the majority-voting approach combines different classification evidence from different classifier outcomes and features through late-fusion techniques. Performed experiments show the proposed data-fusion approaches yield effective results for open-set recognition problems, significantly outperforming existing counterparts in the literature and paving the way for investigations in this field.