Unsupervised cross-domain facial expression recognition method

Abstract

The invention discloses an unsupervised cross-domain facial expression recognition method. The method comprises the following steps: mapping source domain and target domain samples to a common subspace by finding a feature transformation matrix; a parameter-free maximum mean value difference MMD is introduced to measure the distance between edge distribution and conditional distribution between source domain data and target domain data, and the edge distribution and the conditional distribution are jointly aligned in the subspace to minimize the distribution distance between domains. And thentraining the transformed features to obtain a domain adaptive classifier to predict the data label in the target domain. According to the cross-domain facial expression recognition method, the defectthat most of facial expression recognition needs to meet the requirement that the used test set and training set are from the same data set, namely, the training samples and the test samples meet theassumption that the training samples and the test samples are independently distributed in the same way is overcome, label samples do not need to be carried in a target domain, and the cross-domain facial expression recognition effect is improved.

Description

technical field [0001] The invention relates to an unsupervised cross-domain facial expression recognition method, in particular to an unsupervised cross-domain facial expression recognition method based on joint distribution alignment, which belongs to the fields of artificial intelligence, target detection and image classification. Background technique [0002] In the traditional facial expression recognition task, training samples and test samples usually come from the same database, and its task is to learn a classifier by predicting test samples without a given label through a series of labeled training samples. In practical situations, the training set and test set often come from different expression databases. For example, samples collected by different devices, or samples collected in different environments have different feature distributions. This creates a more challenging problem than traditional facial expression recognition, that is, cross-domain facial expre...

AI Technical Summary

Problems solved by technology

Although these techniques have significantly improved the state of the art, their performance is often limited by the amount of labeled data in the training database.

The generality of these algorithms is largely limited due to the high cost of obtaining human-labeled labels.

Images