Aiming at the low efficiency and serious mapping distortion of current mesh parameterization, a mesh parameterization method with limiting distortion was proposed. Firstly, the original mesh model was pre-processed. After inputting the original 3D mesh model, the Half-Edge data structure was used to reorganize the mesh and the corresponding seams were generated by cutting the mesh model. The Tutte mapping was constructed to map the 3D mesh to a 2D convex polygon domain, that is to construct the 2D mesh model. Then, the mesh parameterization calculation with limiting distortion was performed. The Tutte-mapped 2D mesh model was used as the initial data for limiting distortion calculation, and the distortion metric function relative to the original 3D model mesh was established. The minimum value points of the metric function were obtained, which form the mapped mesh coordinate set. The mapped mesh was used as the input mesh to limit the distortion mapping, and the iteration termination condition was set. The iteration was performed cyclically until the termination condition was satisfied, and the convergent optimal mesh coordinates were obtained. In calculating the mapping distortion, the Dirichlet energy function was used to measure the isometric mapping distortion, and the Most Isometric Parameterizations (MIPS) energy function was used for the conformal mapping distortion. The minimum of the mapping distortion energy function was solved by proxy function combining assembly-Newton method. Finally, this method was implemented and a prototype system was developed. In the prototype system, mesh parameterization experiments for limiting isometric distortion and limiting conformal distortion were designed respectively, statistics and comparisons of program execution time and distortion energy falling were performed, and the corresponding texture mapping effects were displayed. Experimental results show that the proposed method has high execution efficiency, fast falling speed of mapping distortion energy and stable quality of optimal value convergence. When texture mapping is performed, the texture is evenly colored, close laid and uniformly lined, which meets the practical application standards.

In order to improve the accuracy and universality of computer-assisted classification algorithm, a Electrocardiography (ECG) beat classification algorithm based on cluster analysis was presented in this paper. The algorithm considered that one patients' ECG beats repeated periodically, and used the method of two-stage cluster analysis, and selecting representative ECG beats, combined with the diagnosis of cardiac physicians to achieve accurate ECG beat classification rate. In order to verify the accuracy of the algorithm, using the internationally standard database MIT-BIH arrhythmia database, the ECG beat classification method and the accuracy evaluation method specified by AAMI/ANSI standard were used to perform simulation experiments, the final overall classification accuracy rate is 99.07%. Compared with Kiranyaz' method(KIRANYAZ S, INCE T,PULKKINEN J, et al. Personalized long-term ECG classification: A systematic approach［J］. Expert Systems with Applications, 2011, 38(4): 3220-3226.), this method does not require specific training step, and the sensitivity of the ECG beats which labeled as S raise to 89.82% from 40.15%, significantly improving classification algorithm's generalization capability.

Grade classification of seed cotton is a major issue that has a significant impact on the agricultural economy. According to the characteristics such as impurities, yellowness and brightness extracted from images of seed cotton, fuzzy pattern recognition was used to improve the classification of cotton grade. A classification model of seed cotton was constructed based on the fuzzy nearness. Fuzzy mathematics was combined with artificial neural network to build up a well improved model and algorithm. Statistical distribution was used to calculate and select the model parameter method. Eventually, the numbers of impurities of different sizes were worked out by using the Euler's numbers of the image. Based on the method of selecting model parameters, the proposed algorithm could be optimized step by step. After full learning, seed cotton classification accuracy rate reached 92%. The experimental results show that the presented algorithm satisfies the actual application needs.