Lie Group Transformations of Objects in Images
نویسندگان
چکیده
Suppose we take a set of greyscale images obtained from videophotography of a moving object in three dimensions, such as an aeroplane, and suppose we compute moments or fourier descriptors, or some other set of smooth features of the resulting image to get a point in a feature space Fn. Then provided we compute enough moments or other descriptors, i.e. provided n is big enough, and provided the object is not symmetric, the result of this is to give a sample of points from a smooth, one-one map of the group of transformations into the feature space. The value of n which is `big enough' is, almost always, 2d+1, where d is the dimension of the group. This result has applications in, for example, interpolating between di erent views of an object. In this paper we state and prove the above result formally, and give some simple applications.
منابع مشابه
Learning the Lie Groups of Visual Invariance
A fundamental problem in biological and machine vision is visual invariance: How are objects perceived to be the same despite transformations such as translations, rotations, and scaling? In this letter, we describe a new, unsupervised approach to learning invariances based on Lie group theory. Unlike traditional approaches that sacrifice information about transformations to achieve invariance,...
متن کاملOn Infinitesimal Conformal Transformations of the Tangent Bundles with the Generalized Metric
Let be an n-dimensional Riemannian manifold, and be its tangent bundle with the lift metric. Then every infinitesimal fiber-preserving conformal transformation induces an infinitesimal homothetic transformation on . Furthermore, the correspondence gives a homomorphism of the Lie algebra of infinitesimal fiber-preserving conformal transformations on onto the Lie algebra of infinitesimal ...
متن کاملLearning Lie Groups for Invariant Visual Perception
One of the most important problems in visual perception is that of visual invariance: how are objects perceived to be the same despite undergoing transformations such as translations, rotations or scaling? In this paper, we describe a Bayesian method for learning invariances based on Lie group theory. We show that previous approaches based on first-order Taylor series expansions of inputs can b...
متن کاملInclined Lorentzian force effect on tangent hyperbolic radiative slip flow imbedded carbon nanotubes: lie group analysis
The present paper focuses on numerical study for an inclined magneto-hydrodynamic effect on free convection flow of a tangent hyperbolic nanofluid embedded with Carbon nanotubes (CNTs) over a stretching surface taking velocity and thermal slip into account. Two types of nanoparticles are considered for the study; they are single and multi-walled nanotubes. The presentation of single-parameter g...
متن کاملThe Geometry of Video Images
Suppose we take a set of images obtained from videophotography of a moving object in three dimensions, such as an aeroplane, and that we compute moments or fourier descriptors, or some other set of smooth features of the resulting image, to get a vector in a feature space F which describes the image. Then the different orientations and positions of the object in space are generated by a local L...
متن کاملA Diffusion Equation with Exponential Nonlinearity Recant Developments
The purpose of this paper is to analyze in detail a special nonlinear partial differential equation (nPDE) of the second order which is important in physical, chemical and technical applications. The present nPDE describes nonlinear diffusion and is of interest in several parts of physics, chemistry and engineering problems alike. Since nature is not linear intrinsically the nonlinear case is t...
متن کامل