基于掌静脉的身份识别方法、装置、存储介质及电子设备
By enhancing palm vein images and utilizing feature fusion technology from a feature extraction model, the problem of identifying users with sparse palm veins was solved, achieving highly accurate and widely applicable palm vein identity recognition.
CN118097729BActive Publication Date: 2026-07-17GRG BANKING EQUIPMENT CO LTD
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- GRG BANKING EQUIPMENT CO LTD
- Filing Date
- 2024-03-19
- Publication Date
- 2026-07-17
AI Technical Summary
Technical Problem
Existing palm vein recognition technology struggles to accurately identify users with varying degrees of palm vein sparseness, resulting in poor recognition performance.
Method used
By acquiring palm vein images of the user to be identified, enhancing them, and then inputting the images into a trained feature extraction model, a fused feature vector is extracted using two feature extraction modules and a feature fusion module. This fused feature vector is then combined with a pre-created user template feature vector library for identity recognition.
Benefits of technology
It improves the accuracy and reliability of identifying users with different palm vein sparseness, reduces the identity recognition failure rate, has a wide range of applications, and has few limitations.
✦ Generated by Eureka AI based on patent content.
Smart Images
Figure CN118097729B_ABST
Abstract
本申请公开了一种基于掌静脉的身份识别方法、装置、存储介质、电子设备及计算机程序产品，该方法包括：获取待识别用户的掌静脉图像；对掌静脉图像进行增强处理，得到增强图像；将掌静脉图像和增强图像输入已训练的特征提取模型中，得到融合特征向量，特征提取模型包括两个特征提取模块和特征融合模块，掌静脉图像和增强图像分别输入不同的特征提取模块中，特征融合模块用于对两个特征提取模块提取的特征向量进行融合；根据已创建的用户模板特征向量库和融合特征向量，对待识别用户进行身份识别，从而能避免因用户掌静脉稀疏而无法提取出有效特征，进而身份识别失败的问题，提高了识别精准性和可靠性，且适用于各种掌静脉稀疏程度的用户。
Need to check novelty before this filing date? Find Prior Art