Image Matching Based on Local Invariant Feature and Histogram-Based Similar Distance

摘要

In this paper we present a novel approach combining local invariant feature descriptor ARPIH (Angular Radial Partitioning Intensity Histogram) with histogram-based similar distance (HSD). The method succeeds the descriptorpsilas distinctiveness and provides higher robustness for image deformations, such as rotation, illumination changing and perspective, etc. We present the HSD to calculate the number of the similar points between template image and target image in order to decrease the calculation complicacy and improve the matching precision. The matching results show good performance of our approach for both geometric deformations and illumination changing.