Spatial-Visual Label Propagation for Local Feature Classification

Tarek El-Gaaly, Marwan Torki, Ahmed Elgammal
2014 2014 22nd International Conference on Pattern Recognition  
In this paper we present a novel approach to integrate feature similarity and spatial consistency of local features to achieve the goal of localizing an object of interest in an image. The goal is to achieve coherent and accurate labeling of feature points in a simple and effective way. We introduced our Spatial-Visual Label Propagation algorithm to infer the labels of local features in a test image from known labels. This is done in a transductive manner to provide spatial and feature
more » ... nd feature smoothing over the learned labels. We show the value of our novel approach by a diverse set of experiments with successful improvements over previous methods and baseline classifiers.
doi:10.1109/icpr.2014.589 dblp:conf/icpr/El-GaalyTE14 fatcat:iwxbstieszanbk5uqpnsk4ihra