Facial key point positioning method based on deep learning and expression recognition
An expression recognition and deep learning technology, applied in neural learning methods, acquisition/recognition of facial features, character and pattern recognition, etc., can solve the problems of large amount of calculation and low robustness of expression key points, and improve the robustness. , the effect of reducing the amount of calculation
Active Publication Date: 2021-08-06
UNIV OF SCI & TECH BEIJING +1
View PDF10 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0008] The purpose of the present invention is to provide a method for locating facial key points based on deep learning and expression recognition, which solves the problems of large amount of calculation and low robustness of expression key points in complex expression recognition systems
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
[0047] In order to make the object, technical solution and advantages of the present invention clearer, the implementation manner of the present invention will be further described in detail below in conjunction with the accompanying drawings.
[0048] Embodiments of the present invention provide a method for locating facial key points based on deep learning and expression recognition, such as figure 1 As shown, the method includes the following steps:
[0049] Select a specific face image with various expressions, and perform expression modeling according to the facial features in the face image;
[0050] Mark the contours of the various organs of the face in the expression model as key point data to construct a data set;
[0051] Preprocess the constructed dataset;
[0052] Build a deep learning network model;
[0053] Input the preprocessed data set into the deep learning network model for training;
[0054] The trained facial key point data set is used for expression c...
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 discloses a facial key point positioning method based on deep learning and expression recognition, and the method comprises the steps: selecting a specific face image of various expressions, and carrying out the expression modeling according to the facial features in the face image; taking contours of all organs of the face in the expression model as key point data for labeling, and constructing a data set; preprocessing the constructed data set; building a deep learning network model; inputting the preprocessed data set into the deep learning network model for training; and applying the trained face key point data set to expression classification and identification prediction. According to the method, information of a whole image does not need to be processed, only the positioned key point information needs to be processed to serve as a data set for expression recognition in various scenes, fast expression classification and recognition prediction can be carried out, the calculation amount is effectively reduced, and the robustness of expression key point recognition is improved.
Description
technical field [0001] The invention relates to the technical field of artificial intelligence and expression recognition, in particular to a method for locating facial key points based on deep learning and expression recognition. Background technique [0002] With the continuous study of science and technology, face key point positioning technology has become one of the main core issues in the study of expression recognition systems, and it is also an indispensable preprocessing process. Even if we use simple face alignment technology to calculate the affine matrix of the image and crop it so that the eyes of the face are horizontal, it can effectively improve the accuracy of the expression recognition system. [0003] Face key point positioning is also called face key point detection (Facial Landmark Detection), that is, the face frame obtained by using a certain method such as a face detector, CNN (Convolution Neural Network, CNN) for face detection, will The vital parts...
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): G06K9/00G06K9/62G06N3/04G06N3/08
CPCG06N3/04G06N3/08G06V40/174G06V40/168G06F18/214
Inventor 胡四泉张超石志国
Owner UNIV OF SCI & TECH BEIJING