Multi-table reinforcement learning for visual object recognition

Abstract:

This paper presents a bag of feature based method for visual object recognition. Our contribution is focussed on the selection of the best feature descriptor. It is implemented by using a novel multi-table reinforcement learning method that selects among five of classical descriptors (i.e., Spin, SIFT, SURF, C-SIFT and PHOW) the one that best describes each image. Experimental results and comparisons are provided showing the improvements achieved with the proposed approach. © 2013 Springer.

Año de publicación:

2013

Keywords:

• Artificial Intelligence
• Object recognition
• reinforcement learning

Fuente:

scopus

google