一种人脸标识方法、装置、计算机设备和存储介质
By extracting facial features and calculating similarity through a multi-layered distributed edge network architecture, a unique facial identification code is generated, which solves the problem of insufficient computing power at the edge and realizes self-contained closed loop and distributed computing at the edge.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- SHENZHEN MIRACLE WISDOM NETWORK CO LTD
- Filing Date
- 2023-02-27
- Publication Date
- 2026-07-17
AI Technical Summary
Current facial recognition technology relies on centralized computing in the cloud, but lacks sufficient computing power at the edge and the ability to form a closed loop.
A multi-layer distributed edge network architecture is adopted to perform pre-defined multi-layer edge processing on image data. Facial feature extraction, similarity calculation and deduplication are performed through nodes in the first, second and third edge layers to generate a unique facial identification code.
It achieves distributed computing at the edge, making full use of edge computing power, solving the problem of facial identification code association across multiple edge computing environments, and realizing a self-contained business loop without relying on centralized cloud computing.
Smart Images
Figure CN116071808B_ABST