Scale‐Space

Lindeberg, Tony

doi:10.1002/9780470050118.ecse609

Cited by 64 publications

(63 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This approach was applied to scale-invariant feature tracking (Bretzner and Lindeberg [21]), local pattern classification (Wiltschi et al [156]), image feature extraction for geon-based object recognition (Lindeberg and Li [116]), fingerprint analysis (Almansa and Lindeberg [3]) and real-time gesture recognition (Bretzner et al [19,20]). Tutorial overviews of parts of the underlying scale-space framework can be found in Lindeberg [94,98,102,103,107,111].…”

Section: Related Workmentioning

confidence: 99%

“…where L pp and L qq denote the eigenvalues of the Hessian matrix ordered such that L pp ≤ L qq (see Lindeberg [100,103] for explicit expressions).…”

Section: New Feature Strength Measures From the Hessian Matrixmentioning

confidence: 99%

“…The context we consider is that we for any two-dimensional image f : R 2 → R define a Gaussian scale-space representation L : R 2 × R + → R according to Iijima [57], Witkin [157], Koenderink [69], Koenderink and van Doorn [72,73], Lindeberg [94,95,103,105,107], Sporring et al [147], Florack [43], ter Haar Romeny [53]:…”

Section: Scale-space Representationmentioning

confidence: 99%

See 2 more Smart Citations

Image Matching Using Generalized Scale-Space Interest Points

Lindeberg

2013

Lecture Notes in Computer Science

Self Cite

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

Section: Related Workmentioning

confidence: 99%

“…where L pp and L qq denote the eigenvalues of the Hessian matrix ordered such that L pp ≤ L qq (see Lindeberg [100,103] for explicit expressions).…”

Section: New Feature Strength Measures From the Hessian Matrixmentioning

confidence: 99%

See 1 more Smart Citation

Image Matching Using Generalized Scale-Space Interest Points

Lindeberg

2013

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

show abstract

“…One of the variations of "bag of features" (B.O.F) method based on SIFT detector and descriptor was first proposed by Lowe in [6]. Other good sources of information about scale space and local features are [7] and [8]. In [9] authors applied the local features to nude or pornographic images detection.…”

Section: Introductionmentioning

confidence: 99%

Enhancing Music Information Retrieval by Incorporating Image-Based Local Features

Kaliciak

Horsburgh

Song

et al. 2012

Information Retrieval Technology

View full text Add to dashboard Cite

Abstract. This paper presents a novel approach to music genre classification. Having represented music tracks in the form of two dimensional images, we apply the "bag of visual words" method from visual IR in order to classify the songs into 19 genres. By switching to visual domain, we can abstract from musical concepts such as melody, timbre and rhythm. We obtained classification accuracy of 46% (with 5% theoretical baseline for random classification) which is comparable with existing state-of-the-art approaches. Moreover, the novel features characterize different properties of the signal than standard methods. Therefore, the combination of them should further improve the performance of existing techniques. The motivation behind this work was the hypothesis, that 2D images of music tracs (spectrograms) perceived as similar would correspond to the same music genres. Conversely, it is possible to treat real life images as spectrograms and utilize music-based features to represent these images in a vector form. This points to an interesting interchangeability between visual and music information retrieval.

show abstract

“…Greenberg, Mayer and Kogan using local histogram equalization, Wiener filtering, and image binarization for Fingerprint Image Enhancement [6]. Tony Lindeberg using scale-space representation with a module for automatic scale selection based on the maximization of normalized derivatives over scales, early visual modules can be made scale invariant [7]. Sepasian, Balachandran and Mares presented a threestep procedure for the fingerprint identification and enhancement, using CLAHE with Clip Limit [8].…”

Section: Introductionmentioning

confidence: 99%