基于SSM与特征精炼的轻量级PPG生物特征识别方法
By adopting a lightweight PPG biometric recognition method based on state-space model and feature refinement, the robustness and real-time performance of PPG biometric recognition in existing technologies are not sufficient, and efficient and stable biometric recognition is achieved on resource-constrained devices.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- QILU UNIVERSITY OF TECHNOLOGY (SHANDONG ACADEMY OF SCIENCES)
- Filing Date
- 2025-12-11
- Publication Date
- 2026-07-17
AI Technical Summary
Existing PPG biometric recognition technology has shortcomings in terms of robustness, real-time performance, and reliability. In particular, its recognition performance is unstable in complex and ever-changing real-world scenarios, and it is difficult to achieve real-time recognition on devices with limited computing resources.
A lightweight PPG biometric identification method based on state space model and feature refinement is adopted. Feature extraction and refinement are performed through a lightweight local feature extraction backbone network and LIMA-Mamba module. Combined with identity perception distance metric and inter-class separation maximization module, the geometric structure of feature space is optimized.
It improves the accuracy, real-time performance, and reliability of PPG biometric recognition, solves the bottleneck of computational efficiency in long-range dependency modeling, the sensitivity of signal distribution offset, and noise interference, and enhances the model's generalization ability and recognition stability in variable scenarios.
Smart Images
Figure CN121685995B_ABST