New methods for recognition of range images based on correlation are p
resented. The techniques allow the detection of a range image of a tri
dimensional pattern whatever its position along the x, y and z axes. T
he first method uses the phase-coding of the range image in order to o
btain invariance along the z-axis in the correlation process. The seco
nd method uses the sine-coding of the range image in order to obtain b
etter discrimination than that obtained with phase-coding. The third m
ethod is a hybrid one that makes use of sine-coding for the input scen
e and phase-coding for the reference image, so both the full translati
on invariance and high discrimination abilities are obtained. Computer
simulations are presented. Also, an experimental implementation of th
e method has been carried out showing good agreement with theoretical
predictions.