An analysis of the factors affecting keypoint stability in scale-space

DOI10.1007/S10851-016-0657-5zbMATH Open1386.68182arXiv1511.08478OpenAlexW2264734580MaRDI QIDQ333634FDOQ333634

Authors: Ives Rey-Otero, Mauricio Delbracio, J. M. Morel 

Publication date: 31 October 2016

Published in: Journal of Mathematical Imaging and Vision (Search for Journal in Brave)

Abstract: The most popular image matching algorithm SIFT, introduced by D. Lowe a decade ago, has proven to be sufficiently scale invariant to be used in numerous applications. In practice, however, scale invariance may be weakened by various sources of error inherent to the SIFT implementation affecting the stability and accuracy of keypoint detection. The density of the sampling of the Gaussian scale-space and the level of blur in the input image are two of these sources. This article presents a numerical analysis of their impact on the extracted keypoints stability. Such an analysis has both methodological and practical implications, on how to compare feature detectors and on how to improve SIFT. We show that even with a significantly oversampled scale-space numerical errors prevent from achieving perfect stability. Usual strategies to filter out unstable detections are shown to be inefficient. We also prove that the effect of the error in the assumption on the initial blur is asymmetric and that the method is strongly degraded in presence of aliasing or without a correct assumption on the camera blur.

Full work available at URL: https://arxiv.org/abs/1511.08478

Recommendations

• Is SIFT scale invariant?
• Computer Vision - ECCV 2004
• Scale selection properties of generalized scale-space interest point detectors
• SIFER: scale-invariant feature detector with error resilience
• Scale Space and PDE Methods in Computer Vision

zbMATH Keywords

scale invarianceSIFTGaussian convolutionkeypoint detectorsscale-space

Mathematics Subject Classification ID

Computing methodologies for image processing (68U10) Machine vision and scene understanding (68T45)

Cites Work

• SIFER: scale-invariant feature detector with error resilience
• Is SIFT scale invariant?
• Title not available (Why is that?)
• Linear scale-space has first been proposed in Japan
• On affine invariant descriptors related to SIFT
• A Statistical Approach to the Matching of Local Features
• Coding images with local features
• The non-parametric sub-pixel local point spread function estimation is a well posed problem

Cited In (4)

• Is SIFT scale invariant?
• SIFER: scale-invariant feature detector with error resilience
• A unified B-spline framework for scale-invariant keypoint detection
• Computer Vision - ECCV 2004

Uses Software

• PCA-SIFT
• Vlfeat
• SIFT
• SURF
• BRISK
• SIFER

This page was built for publication: An analysis of the factors affecting keypoint stability in scale-space

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q333634)