Feature Descriptors: a Review of Multiple Cues Approaches

Feature descriptors have been playing an important role in many computer vision problems, such as image matching and object recognition. While classic descriptors using texture or shape as a single cue of descriptive information have been proved to be successful, recently, several approaches have been proposed introducing the combination of multiple cues to increase descriptive power and robustness. In this paper, we review the methodology of the most recent and popular multiple cues descriptors, and evaluate them with respect to their application and robustness to the variance of conditions.