A robust feature descriptor based on multiple gradient-related features

Zhaomang Sun, Fei Zhou, Qingmin Liao

Abstract: In this paper, we propose a robust descriptor named as multiple gradient-related features (MGRF) in virtue of local and overall order encoding. Specifically, three types of features are introduced, including multidirectional gradient, gradient orientation, and first derivative of gradient orientation, each of which represents different aspect of region of interest (ROI). To extract these features, we also propose a novel sampling pattern of tree structure. Furthermore, each gradient-related feature is encoded with both local and overall order information of ROI, and the encoding results are respectively called local and overall gradient order code (GOC). Finally, our descriptor is formed by concatenating the respective feature vector of each type of feature, which is computed as a 2-D joint histogram of GOC and ordinal bin. The experiments conducted on Oxford dataset demonstrate that the proposed descriptor significantly outperforms other state-of-the-art descriptors.