Software interaction method and system for face recognition and storage medium
A face recognition and interaction method technology, which is applied to systems and storage media, and the field of software interaction methods for face recognition, can solve problems such as adverse user health, and achieve the effects of rich interfaces, rapid data feedback, and small installation packages.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0058] Such as figure 1 As shown, the present embodiment provides a software interaction method for face recognition, and the specific steps of the method are as follows:
[0059] S1: Based on a large number of face data models, combined with AI algorithms, train the marking model of key points of facial recognition under different postures and expressions;
[0060] S2: Use audio equipment to collect sound information, and judge the volume, and use the camera to capture video stream data;
[0061] S3: and according to the different application scenarios, call the collection scheme of different numbers of facial recognition key points;
[0062] S4: Preprocessing the video stream data;
[0063] S5: Combining the marking model of the key points of facial recognition after training, mark the key points of facial recognition under different gestures and expressions of the user in the preprocessed video stream data, and output the coordinate set of each facial recognition key poin...
Embodiment 2
[0088] Such as Figure 5 As shown, the present invention provides a software interaction system for face recognition, which includes: a face recognition key point labeling model training module, an information collection module, an information extraction module, and an information processing module. in:
[0089] Facial recognition key point marking model training module: collect a large number of face images under different poses and expressions, and manually mark them to obtain the actual key point coordinates of the face image, and use the face image as the input of the preset convolutional neural network to obtain The face image predicts the key point coordinates, updates the preset convolutional neural network through regression training, uses the difference between the actual face image key point coordinates and the face image predicted key point coordinates as a loss, and repeats the training until the network parameters converge or reach the maximum The number of itera...
Embodiment 3
[0094] This embodiment takes the balloon blowing game as an example to demonstrate the software operation method:
[0095] (1) Open the software, enter the scene selection interface, click the blowing balloon, enter the interactive window under the scene, and the user starts the operation according to the prompt on the screen;
[0096] (2) Call the front camera and audio equipment of the mobile phone. The camera captures the player's movements. Through the calculation of the key point coordinates, it is determined that the user has mouth opening and closing and pouting movements, indicating that the balloon is starting to blow. If the user's mouth opening and closing is not detected The balloon cannot be blown if the mouth is pouting; the audio device collects the user's voice information, and determines the volume through the volume judgment algorithm. The louder the volume and the longer the duration, the bigger the balloon will be blown until it explodes;
[0097] It should...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com