Structure Oriented Local Image Feature Description

In this paper, we proposed a structure oriented descriptor (SOD) for local image feature description. Different from the traditional methods, we explored the structure information via hierarchical strategy and structure coding elements. Firstly, the support region is partitioned into hierarchical sub-regions according to the intensity orders. Secondly, a pre-designed structure coding image is explored to pooling the features according to the hierarchical sub-regions. The final descriptor is a conjunction of the feature of each sub-region. We evaluated the proposed descriptor on the public dataset and compared it with the state-of-the-art works. The experimental results indicate that the proposed descriptor is robust to image appearance change and outperform the state-of-the-art works in most cases.