Multimodal Pattern Recognition Through Particle Swarm Optimization

In this paper we introduce the idea of descriptor combination by Particle Swarm Optimization and its applications for classification purposes using a recently pattern recognition technique called Optimum-Path Forest (OPF), which interprets the samples of the dataset as the nodes of a given graph, and each arc is weighted by the distance between the corresponding nodes. The method combines different color descriptors for classification in the COREL dataset to further weight the OPF graph arcs by these combined similarities. We show that our proposed approach can provides better accuracies than the individual ones obtained by each descriptor.