A genetic algorithm applied in the three-dimensional reconstruction of digitalized objects

We present a method to fully reconstruct real objects acquired by any means of digitalization and where many scans from different views of point have been made. The current problem is modeled as an optimization problem and solved with a Genetic Algorithm (GA) using a custom fitness function based in regular squared distance minimization (SDM). We present examples to show the applicability of our method to reconstruct full objects as well as a possible application in reverse engineering.

[1]  Paul J. Besl,et al.  A Method for Registration of 3-D Shapes , 1992, IEEE Trans. Pattern Anal. Mach. Intell..

[2]  David E. Goldberg,et al.  Genetic Algorithms in Search Optimization and Machine Learning , 1988 .

[3]  Nicholas J. Radcliffe,et al.  Forma Analysis and Random Respectful Recombination , 1991, ICGA.

[4]  Katsuhiko Sakaue,et al.  Registration and integration of multiple range images for 3-D model construction , 1996, Proceedings of 13th International Conference on Pattern Recognition.

[5]  Helmut Pottmann,et al.  Registration without ICP , 2004, Comput. Vis. Image Underst..

[6]  Tong Lee,et al.  Surface registration using a dynamic genetic algorithm , 2004, Pattern Recognit..

[7]  Lance D. Chambers,et al.  Practical Handbook of Genetic Algorithms , 1995 .

[8]  Kjell Brunnström,et al.  Genetic algorithms for free-form surface matching , 1996, Proceedings of 13th International Conference on Pattern Recognition.

[9]  J. E. Baker,et al.  An analysis of the effects of selection in genetic algorithms , 1989 .

[10]  Robert B. Fisher,et al.  Parallel Evolutionary Registration of Range Data , 2002, Comput. Vis. Image Underst..