To solve the problem of expensive computation caused by a large number of vertexes in the process of mapping texture onto the irregular triangular mesh, this paper proposes a novel parameterization texture mapping method based on the simplification of irregular triangular mesh. First of all, the irregular triangular mesh is simplified by folding the directed edges whose cost is the product of the edge length and its local curvature, while still retaining the local features of the original triangular mesh. Then the simplified irregular triangular mesh is parameterized with the spring-mass mode. Because of the force transitivity performance and the balanced force of inner vertexes, the triangular mesh can be parameterized into a rectangle evenly, which avoids the convergence of texture effectively. Next, to get a more realistic result of texture mapping, the parameterization coordinates of vertexes removed in the process of simplification are retrieved and modified with the spring-mass model according to the topology relationships between reserved vertexes and deleted vertexes. So, we can get the complete parameterization coordinates of vertexes in the irregular triangular mesh. Finally, the texture is mapped onto this irregular triangular mesh. Experiment results show that our algorithms can increase the speed efficiently and yield a more realistic texture.
By optimizing the parameters of neural network and applying it to gait recognition, we propose a gait recognition method based on optimized neural network. And we use gait Gaussian image to replace the most popular gait energy image in gait recognition. In this method, an eight-layer convolution neural network is built and initialized with the parameters of the well trained model Alexnet, which can speed up the model convergence and prevent over-fitting effectively. Compared with the traditional methods,the model training time is shortened and the model's expression ability is enhanced at the same time.Further, the gait Gaussian images of human motion are used to train the optimized neural network and update the parameters of the model, training with gait Gaussian image makes the expression of the model be better than the traditional training with gait energy image. To our knowledge, it is the first time to apply gait Gaussian image based neural network to gait recognition in existing researches, this is a breakthrough in the performance of the algorithm. Thus, we get an optimized neural network that can achieve gait recognition successfully. A satisfactory recognition result of the model was found by lots of experiments, especially when the targets carrying status or wearing coat. The experimental results show that the optimized neural network based gait recognition can speed up the model training. In addition，the optimization strategy well avoids over-fitting of the model, and the use of gait Gaussian image also makes the model better than the previous.