关键词: 逆向工程, 最小二乘支持向量机, 孔洞修补, 三角网格曲面

Abstract: To realize hole repairing of cloud data, a novel algorithm for repairing the holes in triangular mesh surface based on Least-Squares Support Vector Machines (LS-SVM) was put forward. Firstly, the holes were identified and the LS-SVM model was trained by using the triangle vertices which gathered around the holes. Secondly, the new triangle vertices were obtained by triangulating the characteristic polygons of the hole. Finally, coordinated values of the new triangle vertices were optimized by the LS-SVM mode and the holes were repaired. Conclusions of experiments indicated that this method had higher precision and faster processing speed than Artificial Neural Network (ANN). It was proved to be a practical and new way for holes repairing.

Key words: reverse engineering, least-squares support vector machines, hole repairing, triangular mesh surface