RSD-DOG : A New Image Descriptor based on Second Order Derivatives - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2015

RSD-DOG : A New Image Descriptor based on Second Order Derivatives

Résumé

This paper introduces the new and powerful image patch de-scriptor 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 fea-tures/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.
Fichier principal
Vignette du fichier
RSD-DOG.pdf (3.08 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-02114293 , version 1 (29-04-2019)

Identifiants

Citer

Darshan Venkatrayappa, Philippe Montesinos, Daniel Diep, Baptiste Magnier. RSD-DOG : A New Image Descriptor based on Second Order Derivatives. ACIVS 2015 - Advanced Concepts for Intelligent Vision Systems, Oct 2015, Museo Diocesano, Catania, Italy. ⟨10.1007/978-3-319-25903-1_3⟩. ⟨hal-02114293⟩
46 Consultations
70 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More