Facial expression recognition method of improved MobileNet model

Abstract

According to the improved MobileNet network model provided by the invention, the network is further simplified by combining the characteristics of facial expression recognition under the condition ofkeeping the lightweight integral structure of the MobileNet, so that the network receives a 48 * 48 single-channel grayscale picture. In order to reduce the network calculation amount, a depth separable convolution layer in the MobileNetV1 model is reserved. Meanwhile, in order to solve the problem of information loss possibly caused by introduction of a nonlinear activation function after a deepconvolution layer, the nonlinear activation function is directly abandoned after the deep convolution layer, and linear output mentioned in MobileNetV2 is adopted. The network model uses a linear support vector machine to classify facial expressions into a network model. Finally, compared with MobileNetV1 and MobileNetV2, the parameters of the network model are greatly reduced. According to the model, an experiment is carried out on a CK + data set, and good recognition performance is achieved on a test set.

Description

technical field [0001] The invention relates to the problem of static human facial expression recognition in the field of computer vision, in particular to a human facial expression recognition method of an improved MobileNet model. Background technique [0002] Facial expression recognition is a hot topic in the field of computer vision. As a direct expression of human emotions, facial expressions are a form of non-verbal communication. At present, the application fields of facial expression recognition technology are very wide, including human-computer interaction (HCI), security, robot manufacturing, medical treatment, communication, automobile and so on. Automatic facial expression recognition systems are necessary in emerging applications such as human-computer interaction (HCI), online distance education, interactive games, and intelligent transportation. [0003] The focus of facial expression recognition is the extraction of facial expression features. For the ext...

AI Technical Summary

Problems solved by technology

[0004] However, with the continuous development of the deep neural network model, its shortcomings have gradually emerged.

The complexity of the network model and the large number of model parameters make these models only applicable in some specific occasions, and it is difficult for mobile terminals and embedded devices to meet their required hardware requirements

The high hardware requirements required by complex network models limit its application scenarios

Images