Natural scene emotion recognition method based on attention mechanism multi-scale network
An emotion recognition and natural scene technology, applied in the field of emotion recognition, can solve the problems of shooting angle, difficulty in directly identifying emotional state, uneven illumination of faces, etc., to achieve the effect of improving the accuracy.
Pending Publication Date: 2022-05-17
SICHUAN UNIV
View PDF9 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
However, in natural scenes, based on visual information is still the main emotion recognition method, but there are corresponding challenges
First of all, human faces in natural scenes usually have problems such as uneven lighting, occlusion, and shooting angles, which make it difficult to directly recognize their emotional states; Browsing the computer at home can be two different emotional states
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0018] Below in conjunction with accompanying drawing and embodiment the present invention is described in further detail, it is necessary to point out that following embodiment is only used for further description of the present invention, can not be interpreted as the restriction to protection scope of the present invention, those skilled in the art According to the content of the invention above, making some non-essential improvements and adjustments to the present invention for specific implementation shall still belong to the protection scope of the present invention.
[0019] Below in conjunction with accompanying drawing, the scheme of the present invention is described in detail:
[0020] (1) The static image I obtains the character image I through the bounding box B And remove the background image I of the person C , the calculation formula is: where bbox IB Indicates the area where the main character is located, for I B and I C Perform scaling, illumination, br...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention relates to a natural scene emotion recognition method based on an attention mechanism multi-scale network, and mainly relates to emotion recognition of character and scene clue fusion. The method mainly comprises the following steps: for a character branch, extracting features and adding a posture attention mechanism at the same time, and the branch can effectively mine the emotional state of the character; for a scene branch, a multi-scale network is used to enhance local detail features in a scene, and a space attention model is fused to automatically pay attention to an area effective for emotion recognition in the scene. According to the invention, emotion recognition is carried out by fully utilizing respective advantages of figures and scenes, and the accuracy of emotion recognition is improved.
Description
technical field [0001] The invention belongs to the field of emotion recognition, and in particular relates to a natural scene emotion recognition method based on an attention mechanism multi-scale network. Background technique [0002] Emotion recognition is a basic task of computer vision, which is a part of affective computing, which aims to recognize the feelings and states of an individual, such as happiness, sadness, disgust, surprise, etc. Emotion recognition technology has a wide range of uses, and has been applied in human-computer interaction, security, medical health and other fields. [0003] For the research on emotion recognition, whether it is traditional manual feature extraction or deep learning methods, most studies focus on facial features because they can provide the most obvious and intuitive emotional state. Studies have found that voice, text, posture, and physical body signals (heartbeat changes, pupil dilation, etc.) can also assist in the recogniti...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Applications(China)
IPC IPC(8): G06V40/16G06V40/20G06V10/80G06V10/82G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06N3/045G06F18/253
Inventor 卿粼波晋儒龙何小海陈洪刚文虹茜
Owner SICHUAN UNIV