| Most of the Qin Terracotta Warriors had been damaged when excavated.it is complex to be stitch and repair a large number of cultural relics fragments,and the splicing and restoration task of the them has become complicated mathematical problem.The research on the intelligent processing method of high-performance models has become the key to promoting the solution of this problem.Since the intuitionistic fuzzy set considers the three aspects of membership,non-membership and hesitation as the same time,it is more suitable for dealing with the uncertainty degree of "matching" in the process of multi-fragment splicing.And it provides technical support for the fuzzy representation of the shape of the damaged terracotta fragments,the model representation of the missing features,and the problem that it is not easy to extract and represent the features of the damaged terracotta fragments because of its fuzzy,so as to achieve accurate modeling and support a series of calculations in the model feature space.In addition,the swarm intelligence optimization algorithm has unique advantages in solving the problem of large-scale,discrete,nonlinear,multiple constraints,and huge solution space.Therefore,this study combines the intuitionistic fuzzy set theory and the swarm intelligence optimization algorithm to carry out in-depth research on the virtual splicing of fragments.The main contents include:(1)A hybrid particle swarm optimization algorithm(IFEHPSO)based on intuitionistic fuzzy entropy is proposed.An adaptive function of intuitionistic fuzzy entropy is constructed,and the entropy value is used as a disturbance factor to dynamically change the inertia weight.An adaptive global optimal particle learning strategy is established to train the disturbed particles so that the algorithm can maintain the particle diversity.The simulation experiment results show that the algorithm has better performance in solving accuracy and convergence speed.(2)A whale optimization algorithm based on intuitionistic fuzzy niche technology(IFN-SILWOA)is proposed.The initial population is generated through the combination of chaotic sequence and center of gravity reverse learning.The intuitionistic fuzzy niche technology is Used to enhance the diversity of the population in the iterative process of the algorithm.The weight factor and convergence factor are designed to balance the global and local optimization capabilities of the algorithm.The results of simulation experiments show that the improved algorithm is significantly better than other comparison algorithms in terms of convergence accuracy,convergence speed and stability.(3)For the multi-fragment matching problem,a mathematical model is established for the goal that match fragments of the terracotta warriors,and the fragment matching problem is converted into an optimal matching matrix problem.The IFEHPSO algorithm is used to solve the global optimization problem.Aiming at the problems of long search time and low computational efficiency of fragments in the virtual splicing problem,a virtual splicing method of fragments optimized by IFN-SIL-WOA algorithm is used to obtain the translation and rotation parameters of the coordinates,obtain the optimal matrix,and improve the accuracy and efficiency of virtual splicing. |
PDF Full Text Request