Aiming at the low accuracy of large-pose face alignment, a cascade network based on truncated Alexnet is designed and implemented in the paper. The parallel convolution pooling layers are added for concatenating parallel results in the original deep convolution neural network, which improves the accuracy of the output. Sending the intermediate parameter which is the result of each iteration into CNN and iterating repeatedly to optimize the pose parameter in order to get more accurate results of face alignment. To verify the effectiveness of this method, this paper tests on the AFLW and AFLW2000-3D datasets. Experiments on datasets show that the normalized average error of this method is 5.00% and 5.27%. Compared with 3DDFA, which is a current popular algorithm, the accuracy is improved by 0.60% and 0.15%, respectively.
In this paper, a stochastic configured Bayesian neural network (SCBNN) is proposed for solving regression and classification problems. Firstly, stochastic configuration network (SCN) is applied to extract feature. Then, the stochastic configured scheme is applied to Bayesian neural network (BNN) for obtaining the appropriate structure. The extracted features are combined with the original features to compute the output of the network. Further, an integration strategy of the Bayesian model average (BMA) is considered to improve the performance of the network. Some experimental results demonstrate the validity of the proposed method.