A scale selection principle for estimating image deformations

A scale selection principle for estimating image deformations

A basic functionality of a vision system concerns the ability to compute deformation fields between different images of the same physical structure. This article advocates the need for incorporating an explicit mechanism for scale selection in this context, in algorithms for computing descriptors such as optic flow and for performing stereo matching. A basic reason why such a mechanism is essen...

Direct Estimation of Affine Image Deformations Using Visual Front-End Operations with Automatic Scale Selection

This article deals with the problem of estimating deformations of brightness patterns using visual front-end operations. Estimating such deformations constitutes an important subtask in several computer vision problems relating to image correspondence and shape estimation. The following subjects are treated: The problem of decomposing a ne ow elds into simpler components is analysed in detail. ...

Scale selection for supervised image segmentation

Estimating deformations of stationary processes

This paper studies classes of nonstationary processes, such as warped processes and frequency-modulated processes, that result from the deformation of stationary processes. Estimating deformations can often provide important information about an underlying physical phenomenon. A computational harmonic analysis viewpoint shows that the deformed autocovariance satisfies a transport equation at sm...

A New Selection Principle

For topological spaces X, various special families of covers have been extensively studied in the literature, in a framework called selection principles, see the surveys [8, 4, 12]. The main types of covers are defined as follows. Let U be a cover of X. We say that U is a large (respectively, ω-, γ-) cover of X if: (1) Each x ∈ X is covered by infinitely many U ∈ U ; (2) Each finite F ⊆ X is co...