New 2D-Feature Descriptor Free from Orientation Compensation
Manel Benaissa, Abdelhak Bennia · 2018
Feature description and matching are challenging areas in computer vision applications. In this paper, we proposed an orientation invariant feature descriptor without an additional step dedicated to this task. We exploited the information provided by two representations of the image (intensity and gradient) for a better understanding and representation of the feature point and its surroundings distribution. The provided informations are summarized in two cumulative histograms and used in the feature description and matching process. Experiment results show its robustness to image changes.