Critical Nets and Beta-Stable Features for Image Matching

Gu, Shengfeng; Zheng, Ying; Tomasi, Carlo

doi:10.1007/978-3-642-15558-1_48

Cited by 25 publications

(12 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…With the generalized notion of a scale-space primal sketch for differential descriptors used here, we obtain a straightforward and general way to compute a richer family of corresponding bifurcation events for any sufficiently well-behaved differential expression DL. More recently, Gu et al [52] proposed a representation for image matching based on local spatial neighbourhood relations, referred to as critical nets, that possess local stability properties over scale, with close similarities to these ideas.…”

Section: Related Workmentioning

confidence: 99%

Image Matching Using Generalized Scale-Space Interest Points

Lindeberg

2014

J Math Imaging Vis

156

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%

Image Matching Using Generalized Scale-Space Interest Points

Lindeberg

2014

J Math Imaging Vis

156

View full text Add to dashboard Cite

show abstract

“…On one hand, feature detectors and descriptors [21,16,4,20,6] have been developed for capturing visual appearance in an invariant way. On the other hand, online learning algorithms such as Random Forests [2], Boosting [23], Multiple Instance Learning [1] and Nearest Neighbor [7] have been proposed to enhance the trackers' adaptivity to changes of illumination, scale, cluttered background and occlusion.…”

Section: Previous Workmentioning

confidence: 99%

Branch and track

Tomasi

2011

CVPR 2011

Self Cite

View full text Add to dashboard Cite

We present a new paradigm for tracking objects in video in the presence of other similar objects. This branch-andtrack paradigm is also useful in the absence of motion, for the discovery of repetitive patterns in images. The object of interest is the lead object and the distracters are extras. The lead tracker branches out trackers for extras when they are detected, and all trackers share a common set of features. Sometimes, extras are tracked because they are of interest in their own right. In other cases, and perhaps more importantly, tracking extras makes tracking the lead nimbler and more robust, both because shared features provide a richer object model, and because tracking extras accounts for sources of confusion explicitly. Sharing features also makes joint tracking less expensive, and coordinating tracking across lead and extras allows optimizing window positions jointly rather than separately, for better results. The joint tracking of both lead and extras can be solved optimally by dynamic programming and branching is quickly determined by efficient subwindow search. Matlab experiments show near real time performance at 5-30 frames per second on a single-core laptop for 240 by 320 images.

show abstract

“…Our method makes much weaker assumptions on the underlying pattern. Both the recent chains model ( [13]) and critical nets ( [10]) are related in spirit in the sense that they use local contextual image information only to infer locations and encode invariant image features in a graph-based fashion. In [30] the authors present an invariant representation based on straight edge segments on surface discontinuities.…”

Section: Related Workmentioning

confidence: 99%

Discrete texture traces: Topological representation of geometric context

Ernst

Singh

Ramesh

2012

2012 IEEE Conference on Computer Vision and Pattern Recognition

View full text Add to dashboard Cite

Modeling representations of image patches that are quasi-invariant to spatial deformations is an important problem in computer vision. In this paper, we propose a novel concept, the texture trace, that allows sparse patch representations which are quasi-invariant to smooth deformations and robust against occlusions. We first propose a continuous domain model, the profile trace, which is a function only of the topological properties of an image and is by construction invariant to any homeomorphic transformation of the domain. We analyze its theoretical properties and then derive a discrete-domain approximation, the Discrete Texture Trace (DTT). DTTs are designed to be computationally practical and shown by a set of controlled experiments to be quasi-invariant to smooth spatial deformations as well as common image perturbations. We then show how DTTs can be naturally adapted to the incremental tracking problem, yielding highly precise results on par with the state of the art on challenging real data without using heavy machine learning tools. Indeed, we show that with even just using one image at the start of a sequence (i.e. no incremental updating), our method already outperforms four of six state of the art methods of the recent literature on challenging sequences.

show abstract

Critical Nets and Beta-Stable Features for Image Matching

Cited by 25 publications

References 20 publications

Image Matching Using Generalized Scale-Space Interest Points

Image Matching Using Generalized Scale-Space Interest Points

Branch and track

Discrete texture traces: Topological representation of geometric context

Contact Info

Product

Resources

About