Corner detection based on multi-scale and multi-directional Gabor filter

Abstract

In corner detection, the ability of two-dimensional Gabor feature to distinguish corners is not verified, and the description of pixel neighborhood features has defects. As the result, the robustness of corner detection is poor and the positioning accuracy is low. In order to solve the above problems, the directional derivative of the real part of the two-dimensional Gabor filter was used to extract the intensity variation difference of each corner model, with the multi-directional structure tensor and multi-scale screening mechanism, a new corner detection algorithm was proposed. Firstly, the input image was smoothed by the real part of the two-dimensional Gabor filter, and the gray variations in all directions were extracted. Secondly, the multi-directional structure tensor product was constructed by synthesizing the gray-scale variation information of the target pixel in each direction, and the corresponding corner measure was generated. Finally, the non-maximum suppression was used for preliminary screening, and then the target corners were obtained by multi-scale filtering. The performance of the proposed method was compared with seven classical detection algorithms under the conditions of image affine transformation and Gaussian noise interference. The proposed method has better detection robustness, and the positioning accuracy is also verified by matching experiment based on ground truth.

Keywords

• corner detection
• the two-dimensional gabor filter
• the multi-directional structure tensor
• multi-scale screening mechanism
• non-maximum suppression