Robust interest points matching based on local description and spatial constraints

Abstract

Matching of interest points is a key and an essential step in image description and search with local features. In this paper, we present a new matching method based on the prediction validation principle by matching pairs of interest points with their local description and with adding spatial constraints. The proposed method is independent of the detection process in order to obtain robust estimates of matching points under different changes likes scale, orientation, illumination. Our new matching method is based on two main steps: the first step computes local features around interest points. In the second step, we add some spatial constraints in order to enhance the robustness of the matches. The experimental setup shows that the proposed method can produce robust matches with higher repeatability and reasonable computational efficiency compared to some state of the art algorithms.