RSD-DOG : A New Image Descriptor based on Second Order Derivatives
This is an incremental improvement for computer vision researchers and practitioners needing robust image descriptors.
The paper tackles image patch description by introducing RSD-DOG, a descriptor based on second-order derivatives that treats intensity as a third dimension, achieving good discriminative power against variations like illumination, scale, and rotation. Experiments show it outperforms first-order counterparts such as SIFT and DAISY in image matching.
This paper introduces the new and powerful image patch descriptor based on second order image statistics/derivatives. Here, the image patch is treated as a 3D surface with intensity being the 3rd dimension. The considered 3D surface has a rich set of second order features/statistics such as ridges, valleys, cliffs and so on, that can be easily captured by using the difference of rotating semi Gaussian filters. The originality of this method is based on successfully combining the response of the directional filters with that of the Difference of Gaussian (DOG) approach. The obtained descriptor shows a good discriminative power when dealing with the variations in illumination, scale, rotation, blur, viewpoint and compression. The experiments on image matching, demonstrates the advantage of the obtained descriptor when compared to its first order counterparts such as SIFT, DAISY, GLOH, GIST and LIDRIC.