Scale invariance without scale selection

@article{Kokkinos2008ScaleIW,
  title={Scale invariance without scale selection},
  author={Iasonas Kokkinos and Alan Loddon Yuille},
  journal={2008 IEEE Conference on Computer Vision and Pattern Recognition},
  year={2008},
  pages={1-8}
}
  • Iasonas KokkinosA. Yuille
  • Published 23 June 2008
  • Computer Science
  • 2008 IEEE Conference on Computer Vision and Pattern Recognition
In this work we construct scale invariant descriptors (SIDs) without requiring the estimation of image scale; we thereby avoid scale selection which is often unreliable. Our starting point is a combination of log-polar sampling and spatially-varying smoothing that converts image scalings and rotations into translations. Scale invariance can then be guaranteed by estimating the Fourier transform modulus (FTM) of the formed signal as the FTM is translation invariant. We build our descriptors… 
View on IEEE
escholarship.org
100 Citations
Highly Influential Citations
15
Background Citations
42
Methods Citations
45
Results Citations
4

100 Citations

Dense Scale Invariant Descriptors for Images and Surfaces

This work constructs scale-invariant signal descriptors by introducing a method that does not rely on scale selection and relies on a combination of logarithmic sampling with multi-scale signal processing that turns scaling in the original signal domain into a translation in a new domain.

Scale Normalized Radial Fourier Transform as a Robust Image Descriptor

We present a new visual descriptor that combines a multi-scale Laplacian Profile with a Radial Discrete Fourier Transform. This descriptor exists at every position and scale in an image and provides…

Scale-Less Feature-Spatial Matching

  • Chao ZhangTingzhi Shen
  • Computer Science
    2013 International Conference on Digital Image Computing: Techniques and Applications (DICTA)
  • 2013
The discriminability of the Scale-Less SIFT (SLS) descriptor is improved, which is constructed without requiring scale estimation of interest points, to avoid to find stable scales which are difficult to obtain in many cases.

On SIFTs and their scales

This paper turns to the overwhelming majority of pixels, those where stable scales are not found by standard techniques, and shows that representing each pixel as a set of SIFTs, extracted at multiple scales, allows for far better matches than single-scale descriptors, but at a computational price.

SIFTing Through Scales

This paper turns to the overwhelming majority of pixels, those where stable scales are not found by standard techniques, and shows that representing each pixel as a set of SIFTs, extracted at multiple scales, allows for far better matches than single-scale descriptors, but at a computational price.

Dense, Scale-Less Descriptors

This chapter discusses alternative representations designed to capture multiscale appearance, even in image regions where existing methods for scale selection are not effective, and demonstrates how the use of the SLS descriptor can act as an alternative to existing, single scale representations, allowing for accurate dense correspondences between images with scale-varying content.

On Sifts and Their Scales Lihi Zelnik-manor Technion

This paper turns to the overwhelming majority of pixels, those where stable scales are not found by standard techniques, and shows that representing each pixel as a set of SIFTs, extracted at multiple scales, allows for far better matches than singlescale descriptors, but at a computational price.

Match-time covariance for descriptors

NCC-S is proposed, a highly effective descriptor based on classic normalized cross-correlation, designed for fast execution in the Similarity-MTC framework, which suggests that MTC offers fruitful research directions for image matching previously not accessible in the steering based paradigm.

Dense Segmentation-Aware Descriptors

This work exploits segmentation to construct appearance descriptors that can robustly deal with occlusion and background changes, and integrates this idea with D dense SIFT, and also with Dense Scale and Rotation Invariant Descriptors (SID), delivering descriptor that are densely computable, invariant to scaling and rotation, and robust to background changes.

Supervised Image Segmentation with Scale Invariance

This paper presents a supervised approach to detect image structures, with image segmentation as the application and can be think of as a supervised version of Lindeberg’s classical scheme.
...

33 References

Maximally Stable Local Description for Scale Selection

This paper optimizes keypoint detection to achieve stable local descriptors, and therefore, an improved image representation, and compares the authors' detectors to Harris-Laplace and the Laplacian in the context of image matching as well as of category and texture classification.

Image registration using log-polar mappings for recovery of large-scale similarity and projective transformations

A novel technique to recover large similarity transformations (rotation/scale/translation) and moderate perspective deformations among image pairs and achieves subpixel accuracy through the use of nonlinear least squares optimization.

Distinctive Image Features from Scale-Invariant Keypoints

  • D. Lowe
  • Computer Science
    International Journal of Computer Vision
  • 2004
This paper presents a method for extracting distinctive invariant features from images that can be used to perform reliable matching between different views of an object or scene and can robustly identify objects among clutter and occlusion while achieving near real-time performance.

Edge Detection and Ridge Detection with Automatic Scale Selection

  • T. Lindeberg
  • Computer Science
    Proceedings CVPR IEEE Computer Society Conference on Computer Vision and Pattern Recognition
  • 1996
A mechanism is presented for automatic selection of scale levels when detecting one-dimensional image features, such as edges and ridges, with characteristic property that the selected scales on a scale-space ridge instead reflect the width of the ridge.

A performance evaluation of local descriptors

It is observed that the ranking of the descriptors is mostly independent of the interest region detector and that the SIFT-based descriptors perform best and Moments and steerable filters show the best performance among the low dimensional descriptors.

PCA-SIFT: a more distinctive representation for local image descriptors

  • Yan KeR. Sukthankar
  • Computer Science
    Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004.
  • 2004
This paper examines (and improves upon) the local image descriptor used by SIFT, and demonstrates that the PCA-based local descriptors are more distinctive, more robust to image deformations, and more compact than the standard SIFT representation.

Feature Detection with Automatic Scale Selection

  • T. Lindeberg
  • Computer Science
    International Journal of Computer Vision
  • 2004
It is shown how the proposed methodology applies to the problems of blob detection, junction detection, edge detection, ridge detection and local frequency estimation and how it can be used as a major mechanism in algorithms for automatic scale selection, which adapt the local scales of processing to the local image structure.

Groups of Adjacent Contour Segments for Object Detection

It is shown that kAS substantially outperform IPs for detecting shape-based classes, and the object detector is compared to the recent state-of-the-art system by Dalal and Triggs (2005).

Detecting and localizing edges composed of steps

It is well known that the projection of depth or orientation discontinuities in a physical scene results in image intensity edges which are not ideal step edges but are more typically a combination…

Object class recognition by unsupervised scale-invariant learning

The flexible nature of the model is demonstrated by excellent results over a range of datasets including geometrically constrained classes (e.g. faces, cars) and flexible objects (such as animals).