INVARIANT PATTERN-RECOGNITION FOR RANGE IMAGES USING THE PHASE FOURIER-TRANSFORM AND A NEURAL-NETWORK

A method for invariant pattern recognition of range images by means of the phase Fourier transform is introduced. The phase Fourier transfor m may be used for the segmentation of connected planar and quadric sur faces. The method is generalized to nonconnected planar surfaces throu gh the use of the concept of the characteristic normal. An invariant r epresentation under changes of position, scale, and orientation for th e characteristic normals is defined. This representation is used as th e input for a feedforward neural network. Examples of applications are given, and finally the method is applied to the problems of classific ation and occlusion.