Local Scale Selection for Gaussian Based Description Techniques

Chomat, Olivier; Verdière, Vincent Colin de; Hall, Daniela; Crowley, James L.

doi:10.1007/3-540-45054-8_8

Cited by 32 publications

(38 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Later, this idea was generalized to a wide class of differential image features, by selecting scale levels from local maxima over scales of differential invariants expressed in terms of normalized derivatives (Lindeberg 1993b, Lindeberg 1994. This principle has been applied to various problems relating to the detection of image features (Lindeberg 1998b, Lindeberg 1998a, Chomat et al 2000, Almansa & Lindeberg 2000, Pedersen & Nielsen 2000, Nielsen & Lillholm 2001, Kadir & Brady 2001. In particular, and motivated by the observation that single-scale ridge detection may be highly sensitive to the choice of scale level, special emphasis has been on the detection of ridges for medical image analysis , Eberly et al 1994, Koller et al 1995, Lorenz et al 1997, Sato et al 1998, Staal et al 1999, Frangi et al 1999, Majer 2001.…”

Section: Related Workmentioning

confidence: 99%

Real-Time Scale Selection in Hybrid Multi-scale Representations

Lindeberg¹,

Bretzner²

2003

Scale Space Methods in Computer Vision

View full text Add to dashboard Cite

Abstract. Local scale information extracted from visual data in a bottomup manner constitutes an important cue for a large number of visual tasks. This article presents a framework for how the computation of such scale descriptors can be performed in real time on a standard computer.The proposed scale selection framework is expressed within a novel type of multi-scale representation, referred to as hybrid multi-scale representation, which aims at integrating and providing variable trade-offs between the relative advantages of pyramids and scale-space representation, in terms of computational efficiency and computational accuracy. Starting from binomial scale-space kernels of different widths, we describe a family pyramid representations, in which the regular pyramid concept and the regular scale-space representation constitute limiting cases. In particular, the steepness of the pyramid as well as the sampling density in the scale direction can be varied.It is shown how the definition of γ-normalized derivative operators underlying the automatic scale selection mechanism can be transferred from a regular scale-space to a hybrid pyramid, and two alternative definitions are studied in detail, referred to as variance normalization and lp-normalization. The computational accuracy of these two schemes is evaluated, and it is shown how the choice of sub-sampling rate provides a trade-off between the computational efficiency and the accuracy of the scale descriptors. Experimental evaluations are presented for both synthetic and real data. In a simplified form, this scale selection mechanism has been running for two years, in a real-time computer vision system.

show abstract

Section: Related Workmentioning

confidence: 99%

Real-Time Scale Selection in Hybrid Multi-scale Representations

Lindeberg¹,

Bretzner²

2003

Scale Space Methods in Computer Vision

View full text Add to dashboard Cite

show abstract

“…Chomat et al [28] and Hall et al [54] made use of scale selection from local maxima over scales of normalized derivatives for computing scale-invariant Gaussian derivative descriptors for object recognition. Lowe [118,119] developed an object recognition system based on local position dependent histograms computed at positions and scales determined from scale-space extrema of differences of Gaussians, thus with very close similarities to scale-invariant blob detection from scale-space extrema of the Laplacian.…”

Section: Related Workmentioning

confidence: 99%

Image Matching Using Generalized Scale-Space Interest Points

Lindeberg

2014

J Math Imaging Vis

157

View full text Add to dashboard Cite

The performance of matching and object recognition methods based on interest points depends on both the properties of the underlying interest points and the choice of associated image descriptors. This paper demonstrates advantages of using generalized scale-space interest point detectors in this context for selecting a sparse set of points for computing image descriptors for image-based matching. For detecting interest points at any given scale, we make use of the Laplacian ∇ 2 norm L, the determinant of the Hessian det H norm L and four new unsigned or signed Hessian feature strength measures D 1,norm L,D 1,norm L, D 2,norm L and D 2,norm L, which are defined by generalizing the definitions of the Harris and Shi-and-Tomasi operators from the second moment matrix to the Hessian matrix. Then, feature selection over different scales is performed either by scale selection from local extrema over scale of scale-normalized derivates or by linking features over scale into feature trajectories and computing a significance measure from an integrated measure of normalized feature strength over scale. A theoretical analysis is presented of the robustness of the differential entities underlying these interest points under image deformations, in terms of invariance properties under affine image deformations or approximations thereof. Disregarding the effect of the rotationally symmetric scale-space smoothing operation, the determinant of the Hessian det H norm L is a truly affine covariant differential entity and the Hessian feature strength measures D 1,norm L andD 1,norm L have a major contribution from the affine covariant determinant of the Hessian, implying that local extrema of these differen- It is shown how these generalized scale-space interest points allow for a higher ratio of correct matches and a lower ratio of false matches compared to previously known interest point detectors within the same class. The best results are obtained using interest points computed with scale linking and with the new Hessian feature strength measures D 1,norm L,D 1,norm L and the determinant of the Hessian det H norm L being the differential entities that lead to the best matching performance under perspective image transformations with significant foreshortening, and better than the more commonly used Laplacian operator, its difference-of-Gaussians approximation or the Harris-Laplace operator. We propose that these generalized scale-space interest points, when accompanied by associated local scale-invariant image descriptors, should allow for better performance of interest point based methods for image-based matching, object recognition and related visual tasks.

show abstract

“…Dense descriptors for estimating characteristic scales at any image point have been considered by Lindeberg (1998b), Almansa and Lindeberg (2000), Chomat et al (2000) and Hall et al (2000). Pattern representations by scale-invariant image features providing compact object descriptions have been used for recognition by Lowe (1999) and Mikolajczyk and Schmid (2001).…”

Section: Related Workmentioning

confidence: 99%

Untitled

Laptev

Lindeberg

2003

International Journal of Computer Vision

View full text Add to dashboard Cite

Abstract. This paper presents two approaches for evaluating multi-scale feature-based object models. Within the first approach, a scale-invariant distance measure is proposed for comparing two image representations in terms of multi-scale features. Based on this measure, the maximisation of the likelihood of parameterised feature models allows for simultaneous model selection and parameter estimation.The idea of the second approach is to avoid an explicit feature extraction step and to evaluate models using a function defined directly from the image data. For this purpose, we propose the concept of a feature likelihood map, which is a function normalised to the interval [0, 1], and that approximates the likelihood of image features at all points in scale-space.To illustrate the applicability of both methods, we consider the area of hand gesture analysis and show how the proposed evaluation schemes can be integrated within a particle filtering approach for performing simultaneous tracking and recognition of hand models under variations in the position, orientation, size and posture of the hand. The experiments demonstrate the feasibility of the approach, and that real time performance can be obtained by pyramid implementations of the proposed concepts.

show abstract

Local Scale Selection for Gaussian Based Description Techniques

Cited by 32 publications

References 17 publications

Real-Time Scale Selection in Hybrid Multi-scale Representations

Real-Time Scale Selection in Hybrid Multi-scale Representations

Image Matching Using Generalized Scale-Space Interest Points

Untitled

Contact Info

Product

Resources

About