An Evaluation of an Object Recognition Schema Using Multiple Region Detectors
Meritxell Vinyals, Arnau Ramisa, Ricardo José Rodrigues de Toledo · 2008
Abstract. Robust object recognition is one of the most challenging topics in com-puter vision. In the last years promising results have been obtained using local re-gions and descriptors to characterize and learn objects. One of these approaches is the one proposed by Lowe in [1]. In this work we compare different region detec-tors in the context of object recognition under different image transformations such as illumination, scale and rotation. Additionally, we propose two extensions to the original object recognition scheme: a Bayesian model that uses knowledge about region detector robustness to reject more unlikely hypotheses and a final verifica-tion process to check that all final hypotheses are coherent to each other.