Accès direct au contenu

CMLA

Version anglaise

aide

Accueil > Publications > Thèses du CMLA

Anatomy of the SIFT method

le 24 septembre 2015
14h30

Thèse d'Ives Rey-Otero (CMLA)

Ives_Rey_Otero.jpg

Ives_Rey_Otero.jpg

This dissertation contributes to an in-depth analysis of the SIFT method. SIFT is the most popular and the first efficient image comparison model. SIFT is also the first method to propose a practical scale-space sampling and to put in practice the theoretical scale invariance in scale space. It associates with each image a list of scale invariant (also rotation and translation invariant) features which can be used for comparison with other images.

Because after SIFT feature detectors have been used in countless image processing applications, and because of an intimidating number of variants, studying an algorithm that was published more than a decade ago may be surprising. It seems however that not much has been done to really understand this central algorithm and to find out exactly what improvements we can hope for on the matter of reliable image matching methods.

Our analysis of the SIFT algorithm is organized as follows. We focus first on the exact computation of the Gaussian scale-space which is at the heart of SIFT as well as most of its competitors.

We provide a meticulous dissection of the complex chain of transformations that form the SIFT method and a presentation of every design parameter from the extraction of invariant keypoints to the computation of feature vectors. Using this documented implementation permitting to vary all of its own parameters, we define a rigorous simulation framework to find out if the scale-space features are indeed correctly detected by SIFT, and which sampling parameters influence the stability of extracted keypoints. This analysis is extended to see the influence of other crucial perturbations, such as errors on the amount of blur, aliasing and noise.

This analysis demonstrates that, despite the fact that numerous methods claim to outperform the SIFT method, there is in fact limited room for improvement in methods that extract keypoints from a scale-space. The comparison of many detectors proposed in SIFT competitors is the subject of the last part of this thesis. The performance analysis of local feature detectors has been mainly based on the repeatability criterion. We show that this popular criterion is biased toward methods producing redundant (overlapping) descriptors. We therefore propose an amended evaluation metric and use it to revisit a classic benchmark. For the amended repeatability criterion, SIFT is shown to outperform most of its more recent competitors. This last fact corroborates the unabating interest in SIFT and the necessity of a thorough scrutiny of this method.
Type :
Thèses - HDR
Lieu(x) :
Campus de Cachan
Salle des conférences -Pavillon des Jardins






Directeurs / Supervisors

  • Prof. Jean-Michel MOREL
  • Mauricio DelBracio, Phd

Examination committee

Coloma Ballester   (referee)
Joachim Weickert   (referee)
Pablo Musé   (referee)
Patrick Pérez   (examiner)
Frédéric Sur   (examiner)




Recherche d'une actualité

Recherche d'une actualité