C. Y. Liu and Y. H. Chen
A robust method for 3-D surface recognition based on genetic algorithms is proposed in this paper. With the help of a specific least square fitting algorithm, the model-based 3-D surface recognition problem is first converted into an optimization problem. Then. a genetic algorithm is used to solve the optimal problem in order to extract general quadric surfaces. Finally, all the extracted surfaces are classified into specific quadric surface represeutations by a classification table. Our experimental results show that the proposed surface extraction method can reliably extract 3-D surfaces from both 3-D synthetic and 3-D real measurement data.