A Robust Affine Invariant Feature Matching Approach

Abstract

Affine transformation detection can be used in many computer vision and other applications. This paper presents a new method for affine transformation detection. The state-of-the-art methods are mainly divided into two classes. One class is based on complicated descriptors. But this kind of methods need a lot of time to establish and matching the complicated descriptors. The second class is based on probabilistic model. But these methods can not yield good matching result in some difficult conditions. Our method tries to combine the two kinds of methods together, so as to acquire the accuracy and efficiency at the same time.