Micro expression recognition method based on 3D convolution neural network

Abstract

The invention relates to a micro expression recognition method based on a 3D convolution neural network. Based on a constructed 3D convolution neural network (3D-CNN) model, happiness, disgust, depression, surprise as well as five other micro expressions can be recognized effectively. The designed micro expression recognition method is simple and efficient. There is no need to carry out a series of processes such as feature extraction, feature dimension reduction and classification on sample data. The difficulty of preprocessing is reduced greatly. Through receptive field and weight sharing, the number of parameters needing to be trained by the neural network is reduced, and the complexity of the algorithm is reduced greatly. In addition, in the designed micro expression recognition method, through down-sampling operation of a down-sampling layer, the robustness of the network is enhanced, and image distortion to a certain degree can be tolerated.

Description

technical field [0001] The invention relates to a micro-expression recognition method based on a 3D convolutional neural network, which belongs to the technical field of image processing and pattern recognition. Background technique [0002] Micro-expressions are special facial expressions that reflect a person's true inner emotions. It is difficult for people to detect micro-expression with the naked eye, and its duration is very short and its intensity is very weak, about 1 / 25s-1 / 5s. Some researchers also believe that its duration is less than 450ms. Due to these characteristics of micro-expression, it has a wide application prospect in the fields of polygraph detection, clinical diagnosis and interrogation. [0003] In the early days, researchers were studying micro-expressions through psychological methods, and they all focused on the recognition of individual micro-expressions. The first micro-expression training tool, METT (Micro Expression Training Tool), was creat...

AI Technical Summary

Problems solved by technology

[0007] The technical problem to be solved by the present invention is to provide a method to solve the problems of complex feature extraction and feature dimensionality reduction in traditional micro-expression recognition, extract features from the dimensions of space and time, and perform 3D convolution to capture images obtained from multiple consecutive frames. Motion information, a micro-expression recognition method based on 3D convolutional neural network that can effectively improve the performance of micro-expression recognition

Images