Saved in:
Bibliographic Details
Main Authors: Venkatrayappa, Darshan, Montesinos, Philippe, Diep, Daniel, Magnier, Baptiste
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2408.07687
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914912962347008
author Venkatrayappa, Darshan
Montesinos, Philippe
Diep, Daniel
Magnier, Baptiste
author_facet Venkatrayappa, Darshan
Montesinos, Philippe
Diep, Daniel
Magnier, Baptiste
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2408_07687
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle RSD-DOG : A New Image Descriptor based on Second Order Derivatives
Venkatrayappa, Darshan
Montesinos, Philippe
Diep, Daniel
Magnier, Baptiste
Computer Vision and Pattern Recognition
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.
title RSD-DOG : A New Image Descriptor based on Second Order Derivatives
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2408.07687