Face silence living body detection method and device, terminal and storage medium
A living body detection and living body technology, applied in the direction of instruments, character and pattern recognition, computer parts, etc., can solve the problems of poor operation, poor friendliness, not in line with the development trend of mobile terminal popularization, etc., to achieve smooth processing and improve The effect of detection accuracy
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0043]Such asfigure 1 As shown, this embodiment provides a human face silent vivo detection method, including the following steps:
[0044]S1, to detect the human face image input to the people's face image to detect, obtain the first classification confidence value;
[0045]S2, will detect the human face image input to the Mobilenetv3-Large network model to detect, obtain the second classification confidence value;
[0046]S3, the average degree of confidence value is obtained for the first classification confidence value and the second classification confidence value;
[0047]S4, it is determined whether the average confidence value exceeds the pre-set reliability threshold. If the output result is a living body, if the output result is an inactive.
[0048]The present invention adopts the Mobilenetv3 network model for human face silent vivo detection, suitable for mobile terminals; and based on the average value of two confidence, the Mobilenetv3-SMALL network model is implemented to assist the...
Embodiment 2
[0080]Such asFigure 4 As shown, on the basis of the embodiment, the present embodiment provides a human face silent living body detecting device, including the following functional modules:
[0081]The first detection module 101: detects the MobileNetv3-Small network model to be detected to be detected to obtain the first classification confidence value;
[0082]Second Detection Module 102: Detects the people's face image to be detected by the MobileNetv3-Large network model to obtain the second classification confidence value;
[0083]The average confidence value calculation module 103: the first classification confidence value and the second classification confidence value obtain average average confidence value;
[0084]The living determination module 104: determines whether or not the average confidence value exceeds the pre-set reliability threshold, if the output result is a living body, if it is not exceeded, the output is an inactive.
[0085]In order to obtain a face image to be detected,...
Embodiment 3
[0090]This embodiment provides a terminal that includes a processor and a memory.
[0091]Memory is used to store the execution instruction of the processor. Memory can be implemented by any type of volatile or non-volatile storage terminal or a combination thereof, such as a static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), can be erased programmable Read-only memory (EPROM), programmable read only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, disk or disc. When the execution instruction in the memory is executed by the processor, the terminal can perform some or all of the steps in the above method embodiment.
[0092]The processor is the control center of the storage terminal, and various portions of the entire electronic terminal are connected by various interfaces and lines, and the software programs and / or modules stored in the memory are operated by running or executing data stored in the memory, and the data...
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