Image Matching Using Generalized Scale-Space Interest Points

Abstract

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.

A Scale-Space Toggle Operator for Image Transformations

“…Figure 11 shows the segmentation results for the mentioned algorithms and for the operator defined by Eq. (9). We can observe that, while the defined operator is robust to different classes of ill-illuminated images, the performance of the other methods was significantly affected.…”

“…[9][10][11] In the following, after a brief review of the classical linear scale-space, we concentrate on the morphological scale-spaces, which possess particular feature-preserving advantages for image processing applications.…”

Antiblurry Dejitter Image Stabilization Method of Fuzzy Video for Driving Recorders

“…Shi-Tomasi was an improved form of Harris [17][18][19] that was determined by gray variation of an image. The Taylor expansion of a gray variation of one image can be expressed as:…”

Remotely-controlled orthodontics: fundamentals and description of the Dental Monitoring system

“…On one hand, algorithms of image analysis and optimization are used and information cards are produced from the series of photographs sent by the mobile application. On the other hand, the precise morphological measurement of the teeth resulting from the initial 3D model of patients' arches in occlusion will permit the calculation of a revised version of the 3D model of the arches 1,10,21,27,39 .…”