A new feature descriptor and selection method to space image registration

In order to extract the flat feature stars, which are used to implement the space image registration, a feature descriptor based on WLD (Weber Local Descriptor) and feature dynamic selection method is proposed in this paper. Firstly, the feature stars are extracted and described by excitation and orientation using the WLD transform. Then we utilize a dynamic feature selection algorithm (DFSA), which is used in registration method selection for registering image with varying scene content, to choose the best match features for the registration. Many space images are used to test the method proposed in this paper and the results show that this method has higher performance compared to traditional methods.