Local descriptors fusion for mobile iris verification
Naiara Aginako, J.M. Martinez-Otzerta, Basilio Sierra, Modesto Castrillón-Santana, Javier Lorenzo-Navarro · 2016
This paper summarizes the proposal submitted by the joint team conformed by researchers from UPV and ULPGC to the Mobile Iris CHallenge Evaluation II. The approach makes use of a state-of-the-art iris segmentation technique, to later extract features making use of local descriptors. Those suitable to the problem are selected after evaluating a collection of 15 local descriptors, covering a range of different grid configuration setups. A Machine Learning approach is used, learning a supervised classifier to deal with the descriptors data. A classifier is obtained for each descriptor, and the best ones are combined in a multi-classifier system. The final step fuses the classifier outputs obtained for 5 different local descriptors, to compute the dissimilarity measure for a pair of iris images.