Properties of Patch Based Approaches for the Recognition of Visual Object Classes

摘要

Patch based approaches have recently shown promising results for the recognition of visual object classes. This paper investigates the role of different properties of patches. In particular, we explore how size, location and nature of interest points influence recognition performance. Also, different feature types are evaluated. For our experiments we use three common databases at different levels of difficulty to make our statements more general. The insights given in the conclusion can serve as guidelines for developers of algorithms using image patches.