Domain-self-adaptive facial expression analysis method

Abstract

The invention relates to a domain-self-adaptive facial expression analysis method and belongs to the field of computer vision and emotion computing research. The method aims to solve the problem that the prediction precision is hindered by training and test data domain differences in automatic expression analysis, and is more aligned with the actual needs. The invention provides the domain-adaptive expression analysis method based on an object domain. The method comprises the following steps: defining a data domain for each tested object; defining the distance between object domains in a way of establishing an auxiliary prediction problem; selecting a group of objects similar to the data character of the tested object from a source data set to form a training set; on the training set, directly using part of tested object data in model training in a way of weighted cooperative training, and thus enabling a prediction model to be closer to the tested object domain. The method has the advantages that the isolation problem of training and testing data is solved, and the prediction model is adaptive to the testing data domain; the method has robustness for the domain differences and is wide in range of application.

Description

technical field [0001] The invention belongs to the research field of computer vision and emotional computing, in particular to an automatic facial expression analysis method. Background technique [0002] Automatic facial expression analysis is a long-standing research problem in computer vision. The goal of mainstream automatic expression analysis is to extract a series of facial action units with semantic-level information from images or videos. Usually the definition in the FACS manual is used. FACS (Facial Action Coding System) is a subdivision and labeling system proposed by behavioral psychologists to study facial expressions. The FACS system decomposes facial movements into a series of expression unit (Action Unit, AU). Each action unit is associated with one or more facial muscle movements. [0003] Most of the current expression analysis research assumes that the training (source) data and test (target) data come from the same data distribution. The following ...

AI Technical Summary

Problems solved by technology

[0006] The purpose of the present invention is to solve the problem that the difference between training and test data domains in expression analysis hinders the prediction accuracy, so that the expression analysis system is more suitable for the actual application environment

Images