Skip to Main content Skip to Navigation
New interface
Journal articles

Three-dimensional invariants and their application to object recognition

Abstract : Although recognition of objects from2Dprojections (i.e. images) has been widely studied among the image processing community, little research has been devoted to recognition using3Dinformation. A general approach for deriving3Dinvariantsis proposed in this paper. These invariants can be used as input to a statistical classifier, such as a k-nearest-neighbours algorithm or a neural network. The approach consists of decomposing the object onto an orthonormal basis composed of the eigenvectors of the angular momentum operator from quantum mechanics.Then, using Clebsch-Gordan coefficients, contravariant tensors of order1areconstructed, and3Dinvariants are obtained by tensor contraction. The approach offers an alternative to structural methods for 3D object description and recognition.Experimental results are provided to illustrate the method.
Document type :
Journal articles
Complete list of metadata
Contributor : Gilles Burel Connect in order to contact the contributor
Submitted on : Sunday, May 9, 2021 - 7:30:39 PM
Last modification on : Thursday, May 13, 2021 - 8:10:17 PM


  • HAL Id : hal-03221750, version 1



Gilles Burel, Hugues Henocq. Three-dimensional invariants and their application to object recognition. Signal Processing, 1995, 45 (1), pp.1-22. ⟨hal-03221750⟩



Record views