Contour-based corner detection via angle difference of principal directions of anisotropic Gaussian directional derivatives

• Anisotropic directional derivatives are applied to corner detection of images.
• A corner detector using the principal direction of the anisotropic directional derivatives is presented.
• The detector is compared with the three state-of-the-art corner detector.
• The detector behaves better in detection, localization, repeatability, and noise robustness.

This paper presents a contour-based corner detector using the angle difference of the principal directions of anisotropic Gaussian directional derivatives (ANDDs) on contours. The noise -robust ANDDs can characterize fine directional intensity variations around edge pixels and corners. The proposed corner detector consists of three steps: Extraction of edge map by the Canny edge detector, improvement of contours by the Douglas-Peucker (D-P) polygonal approximation and filling small gaps between contours, and finding corners from contours by using the angle difference of the principal directions of the ANDDs as the corner measure. Different from the existing contour-based detectors where corner measures correspond to the geometric properties of a contour, the new corner measure utilizes the directional intensity variations at the pixels on a contour and thus has high angular resolution, good localization, and noise-robustness. The proposed detector is compared with the three state-of-the-art detectors from two aspects. Two test images with ground truths are used to assess its detection capability and localization accuracy. Twenty-four test images with various scenes and without ground truths are used to evaluate its repeatability under affine transforms, JPEG compression, and noise degradation. The experimental results show that the proposed detector attains better overall performance.