Abstract
As an important part of emotion research, facial expression recognition is a necessary condition for intelligent interaction between human and machine, which has an important research significance and a potential commercial value. Convolutional neural network (CNN) is an effective method to recognize facial emotions, which can perform feature extraction and classification simultaneously, and can automatically discover multiple levels of representations in data. Due to the fact that there are millions of parameters involved in training the convolutional neural network model, and there is a large demand for marked samples, transfer learning is often used to fine-tune the pre-trained model for a small target sample set. However, there are often some content differences between data sets during deep transfer learning, which will affect the recognition ability of feature extraction. In order to improve the facial expression recognition ability in transfer learning, a hybrid transfer learning model based on an improved convolution restricted boltzmann machine (CRBM) model and a CNN model is proposed in this paper. This method is fused by two learning abilities of these two models. When the pre-trained CNN model is transferred to a small target set, the CRBM is used to replace the full connection layer in the CNN model, and the CRBM layer and the sofmax layer will be retrained on the target set. The added CRBM layer can not only fully connects all feature maps, but can also learn about the unique statistical characteristics about the target set, which eliminates the influence of content differences between data sets, and extracts higher-order statistical features of facial expression images from the target set. The proposed method is evaluated based on four publicly available facial expression databases: JAFFE, FER2013, SFEW and RAF-DB. The new method can achieve better performance than most state-of-the-art methods, and it can effectively prevent the negative influence of transfer learning features between different data sets.
Highlights
Facial expression recognition plays a central role in humancomputer interaction
In order to solve the above problems, this paper proposes a hybrid transfer learning model based on an improved Convolutional restricted Boltzmann machine (CRBM) and a Convolutional neural network (CNN) model
The transfer learning based on the deep convolutional neural network means that the pre-trained deep CNN model is re-trained on the data set of the new target task
Summary
Facial expression recognition plays a central role in humancomputer interaction. In a basic communication course, 55% of the information is conveyed by different facial expressions, The associate editor coordinating the review of this manuscript and approving it for publication was Michele Nappi. The classification method should be applied to perform facial expression recognition, such as SVM, random forest, sparse coding, neural network, etc. These methods have achieved great success in specific fields, most methods can only obtain the low-level features, and can’t obtain the high-level semantics. Convolutional neural network is a very effective method to recognize facial emotions They can perform the feature extraction and classification process simultaneously [11], and can automatically discover multiple levels of representations from data. The transfer learning algorithm solves the fitting problem of small samples in training one CNN model, the ability of the feature recognition will reduce because the content differences between the two data sets.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
