Facial expression action unit adversarial synthesis method based on local attention model

Abstract

The invention relates to the fields of computer vision, emotion calculation and the like. In order to improve the diversity and the universality of an AU expression data set are improved, a technicalscheme adopted by the invnetion includes a facial expression action unit adversarial synthesis method based on a local attention model, and the method comprises the steps: carrying out the feature extraction of a facial motion unit AU region through the local attention model, carrying out the adversarial generation of a local region, and finally carrying out the AU intensity evaluation of enhanceddata, so as to detect the quality of a generated image. The method is mainly applied to occasions such as image processing and face recognition.

Description

Technical field: [0001] The present invention relates to the fields of computer vision and affective computing, and in particular to a method for synthesizing human facial expression motion units based on the combination of Conditional Adversarial Autoencoder (CAAE) and Local Attention Model (Local AttentionModel). It can be widely used in applications such as data enhancement and improving the accuracy of facial expression recognition models. Background technique: [0002] Facial expressions can reveal people's inner activities, mental state, and social behaviors that are communicated outwards. With the development of artificial intelligence, human-centered facial expression recognition has gradually attracted widespread attention in the industry and academia. In the field of facial expression analysis, there are two main ways to label human expressions: labeling based on emotional categories (such as joy, anger, etc.) and labeling based on the Facial Action Coding System ...

AI Technical Summary

Problems solved by technology

[0004] Due to the complexity of facial AU annotation, and it is easily affected by different face shapes, different expressions, different lighting and facial postures, the synthesis of facial expression motion units based on AU annotation still faces many challenges and difficulties, and it is difficult to be widely used.

However, the existing technologies for AU generation generally have problems such as loss of details and lack of authenticity.

Images