Living body face detection model training method and device, apparatus and storage medium
A face detection and training method technology, applied in the field of artificial intelligence, can solve problems such as poor robustness, difficulty in resisting environmental noise, and lack of high prediction accuracy, and achieve strong robustness and high prediction accuracy.
Active Publication Date: 2021-06-29
PING AN TECH (SHENZHEN) CO LTD
View PDF12 Cites 7 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0005] The embodiment of the present invention provides a training method, device, equipment and storage medium of a live face detection model to solve the problem that the current live face detection model is difficult to resist the environment Noise and poor robustness lead to technical problems that do not have high prediction accuracy in real scenarios
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
[0033] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are some of the embodiments of the present invention, but not all of them. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without creative efforts fall within the protection scope of the present invention.
[0034] The training method of the live face detection model provided by this application can be applied in such as figure 1 An application environment in which the computer device communicates with a server through a network. The computer equipment can be, but is not limited to, various personal computers, laptops, smartphones, tablets, and portable wearable devices. The server can be implemented by an independent server or a server cluster composed o...
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 living body face detection model training method, which is applied to the technical field of artificial intelligence and is used for solving the technical problem that the current living body face detection model does not have higher prediction accuracy in a real scene. The method provided by the invention comprises the following steps of acquiring the face sample image sets belonging to different fields; selecting teacher networks in one-to-one correspondence with the fields, and performing dichotomy training on the corresponding teacher networks through the face sample image sets; freezing the trained teacher network; outputting the face image as a prediction probability of a living body face through each teacher network; taking the average value of the output prediction probabilities as a target probability value of a student network to train the student network; and taking the parameter of a feature extractor of the trained student network as the initial value of the parameter of a feature extractor in the living body face detection model, and performing meta-learning training on the living body face detection model through the face sample image sets until a loss function of the living body face detection model is converged.
Description
technical field [0001] The present invention relates to the technical field of artificial intelligence, in particular to a training method, device, equipment and storage medium for a living human face detection model. Background technique [0002] With the upgrading of mobile phones and the rapid development of shooting and processing technology, fraudulent means of non-face live images fake face live images have emerged in an endless stream. At present, the recognition of face live images is generally through the trained live face detection model. Prediction, when the prediction recognizes a non-human face, the user needs to further check whether the face image is a living human face image. [0003] During the training process of the live face detection model, we found that the prediction accuracy of the trained live face detection model will be limited by the type of face image samples participating in the training, for example, when the face image samples participating in...
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): G06K9/00G06N3/04G06N3/08
CPCG06N3/08G06V40/161G06V40/168G06V40/172G06N3/047
Inventor 喻晨曦
Owner PING AN TECH (SHENZHEN) CO LTD