Image Feature Description Based on Local Intensity Comparison
Yixiang Lu, Dan Ma, Jikai Tang, Xueming Peng · 2019
Due to the poor performance of traditional descriptors to complicated illumination and orientation estimation, this paper presents a method for image feature region description based on local intensity comparison. First, the invariant regions of interest are divided into several subregions according to the intensity order. Then, the descriptor is calculated by comparing the value of local neighboring pixels. This method combines overall information and local information together. The experimental results show that the proposed descriptor is not only invariant to monotonic intensity changes and image rotation, but also robust to many other geometric and photometric transformations.