Natural occlusion expression recognition method and system with accurate attention

Abstract

The invention provides a natural occlusion expression recognition method and system with accurate attention, and the method comprises the steps: obtaining a to-be-recognized image, and carrying out the preprocessing of the image; processing the preprocessed to-be-recognized image by using a pre-trained natural occlusion expression recognition network to obtain an expression recognition result; the construction and training process of the natural occlusion expression recognition network comprises the steps of performing face key point detection on an occlusion expression image after preprocessing of a known expression, screening a plurality of interest points in key points, generating a Gaussian graph based on each interest point, and obtaining an occlusion indication graph of the corresponding image; an attention descriptor is calculated according to a neuron activation value of the depth feature of the occlusion expression image, the attention descriptor of the depth feature is forced to approach the occlusion indication graph by constructing attention loss, and attention of the depth feature is forced to adapt to different expressions by constructing expression classification loss. The method is high in recognition accuracy.

Description

technical field [0001] The invention belongs to the technical field of expression recognition, and in particular relates to a method and system for recognizing natural occlusion expressions with accurate attention. Background technique [0002] The statements in this section merely provide background information related to the present invention and do not necessarily constitute prior art. [0003] In recent years, since facial expression recognition plays an important role in many applications such as emotional computing, behavior prediction, human-computer interaction, and mental health services, its research has received widespread attention and achieved great success. When recognizing expressions in the real world, it is common for faces to be occluded by sunglasses, facial accessories such as scarves, or other random objects such as hands, hair, and mugs. The existing facial expression recognition methods are good for the recognition of ideal unoccluded facial expressio...

AI Technical Summary

Problems solved by technology

At present, such researches either allow the network to learn attention weights without any occlusion information, and the learned attention weights are not accurate enough, or use occlusion information to directly weight deep features, and the attention composed only of occlusion information does not Not suitable for the attention of facial expression recognition tasks, so it is not accurate enough

For example, the attention map learned without any occlusion information may still contain part of the occlusion area; another example, the key expression information of an occluded disgust expression image is in the nose and mouth area, and an occlusion The key information of the surprised expression image is in the eyes and mouth area, and the occlusion information can only indicate which area is occluded, and the key areas such as eyes, nose, and mouth without occlusion are treated equally, and it is not suitable for specific expressions.

Images