Migration convolution neural network method for facial expression recognition

Abstract

The invention discloses a migration convolution neural network method for face expression recognition, which comprises the following steps: S1, acquiring a face expression image data set, dividing thedata set into a training set, a verification set and a test set; 2, cascade that migration network and the convolution neural network to construct a migration convolution neural network model; The input of MCN model is facial expression image data, and the output is facial expression category. 3, train that migration convolution neural network model by using a training set, and optimize the trained migration convolution neural network model by using a verification set; S4, the facial expression recognition accuracy of the test set is tested by the optimized migration convolution neural network model. The invention utilizes the migration convolution neural network to recognize the facial expression, and solves the problems that the small data set cannot be converged and over-fitted on a large number of networks.

Description

technical field [0001] The invention relates to the technical field of image recognition, in particular to a migration convolutional neural network method for facial expression recognition. Background technique [0002] Facial expression recognition is an important part of human-computer interaction and affective computing research. With the development of artificial intelligence and the maturity of the robot manufacturing system, the field of human-computer interaction has shown huge market and application prospects. [0003] Traditional facial expression recognition research methods are mainly based on geometric features, and facial expression recognition is performed on human eyes, eyebrows, mouth and other positional changes. Both need to manually set features, the amount of information to extract features is quite limited, and the accuracy rate is difficult to meet the application requirements. [0004] With the development of high-performance servers, deep learning a...

AI Technical Summary

Problems solved by technology

[0005] In order to overcome the deficiencies in the prior art, the present invention provides a migration convolutional neural network method for facial expression recognition, using the migration convolutional neural network to recognize facial expressions, which solves the problem that small data sets cannot converge on a large number of networks and the problem of overfitting

Images