Three-dimensional pattern recognition using fringe projection

A real time system for three-dimensional (3-D) object recognition based on Fourier transform profilometry technique is presented. We demonstrate the performance of the proposed method in two different types of correlators: the joint transform correlator and the classical convergent correlator. The projection of a regular fringe pattern onto the 3-D object surface permits to obtain a distorted grating pattern that carries all the 3-D information of the object. The analysis of such patterns is the basis of the method for recognizing 3-D objects in real time. With this method is also possible to obtain rotation-invariant and scale-invariant 3-D object recognition. The experimental results demonstrate the theory and show the utility of the proposed method.