Local feature descriptor using entropy rate

Over the past decades, an increasing number of local feature descriptors have been proposed in the community of computer vision and pattern recognition. Although they have achieved impressive results in many applications, how to find a balance between accuracy and computational efficiency is still an open issue. To address this issue, we present a local feature descriptor using entropy rate (FDER), which is robust to a variety of image transformations. We first employ the nonsubsampled Contourlet transform to produce multiple support regions and design a graph structure to describe the sub-region. We then use the entropy rate of random walks on the designed graph to build the FDER descriptor. Extensive experiments demonstrate the superiority of proposed descriptor dealing with various image transformations in comparison with the existing state-of-the-art descriptors.