This paper deals with a novel approach for achieving real-time surface recognition. The aim of this study is to detect different kinds of surfaces using a phase-shift range finder and a neural network (NN). The NN architecture is a multilayer perceptron with two inputs, three processing neurons in the hidden layer, and one output neuron. The first and the second inputs receive respectively the amplified and filtered photoelectric signal and the range finder output signal. The NN output is compared with threshold voltages in order to classify the tested surfaces. This recognition system has been studied with data from experimental measurements, achieved with four kinds of surfaces (a plastic surface, a glossy paper, a painted wall, and a porous surface), at a remote distance between the range finder and the target varying from 0.5 to 2 m and with a laser beam incidence angle with respect to the target varying between -π5 and π/5.