This paper proposes a new method based on a multiple branch cross-connected convolutional neural network (MBCC-CNN) for facial expression recognition. Compared with traditional machine learning methods, the proposed method can extract image features more effectively. In addition, in contrast to single-structure convolutional neural networks, the MBCC-CNN model is constructed based on the residual connection, Network in Network, and tree structure approaches together. It also adds a shortcut cross connection for the summation of the convolution output layer, which makes the data flow between networks more smooth, improves the feature extraction ability of each receptive field. The proposed method can fuse the features of each branches more effectively, which solves the problem of insufficient feature extraction of each branches and increases the recognition performance. The experimental results based on the Fer2013, CK+, FER+ and RAF data sets show that the recognition rates of the proposed MBCC-CNN method are 71.52%, 98.48%, 88.10% and 87.34%, respectively. Compared with some most recently work, the proposed method can provide better facial expression recognition performance and has good robustness. INDEX TERMS Facial expression recognition; Convolutional neural network; Residual connection; Network in Network; Robustness.

With the rapid development of deep learning technology, a variety of network models for classification have been proposed, which is beneficial to the realization of intelligent waste classification. However, there are still some problems with the existing models in waste classification such as low classification accuracy or long running time. Aimed at solving these problems, in this paper, a waste classification method based on a multilayer hybrid convolution neural network (MLH-CNN) is proposed. The network structure of this method is similar to VggNet but simpler, with fewer parameters and a higher classification accuracy. By changing the number of network modules and channels, the performance of the proposed model is improved. Finally, this paper finds the appropriate parameters for waste image classification and chooses the optimal model as the final model. The experimental results show that, compared with some recent works, the proposed method has a simpler network structure and higher waste classification accuracy. A large number of experiments in a TrashNet dataset show that the proposed method achieves a classification accuracy of up to 92.6%, which is 4.18% and 4.6% higher than that of some state-of-the-art methods, and proves the effectiveness of the proposed method.

No abstract

No abstract

No abstract