A palm vein edge refinement detection method integrating cross self-attention
By fusing the cross-self-attention method, the local details and global structure of the palm vein image are extracted, and the features are fused in space and channels. Finally, the uncertain points are refined, which solves the problem of poor palm vein edge detection and improves the recognition accuracy.
CN120259352BActive Publication Date: 2025-09-05ANHUI UNIV
2 Cites 0 Cited by
Patent Information
- Application Number
- CN202510380820.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2025-03-28
- Publication Date
- 2025-09-05
- Estimated Expiration
- 2045-03-28
AI Technical Summary
Technical Problem
Images acquired by palm vein recognition technology under near-infrared light are prone to poor edge detection due to uneven lighting, changes in palm posture, or differences in individual vein structure, thus affecting recognition accuracy.
Method used
A palm vein edge refinement detection method integrating cross self-attention is adopted. The feature extraction unit is used to extract local details and global structures, the feature fusion unit is used to fuse features of different scales in space and channels, and the feature refinement unit is used to refine the uncertain points in the preliminary prediction results.
Benefits of technology
The accurate segmentation of palm vein edges is achieved, which improves the accuracy and recognition rate of edge detection.
✦ Generated by Eureka AI based on patent content.
Abstract
The present invention provides a palm vein edge refinement detection method that incorporates cross-self-attention. The method comprises: obtaining a palm vein image to be processed; inputting the image into a trained palm vein edge refinement detection network to obtain edge information. The palm vein edge refinement detection network comprises a feature extraction unit for extracting local details and global structure, a feature fusion unit for fusing features of different scales in space and channels, and a feature refinement unit for segmenting the fused features. The method first extracts local details and global features using the feature extraction unit, then uses the feature fusion unit to aggregate features of different scales in space and channels, and finally uses the feature refinement unit to specifically refine uncertain points in the initial prediction results, thereby achieving accurate segmentation of palm vein edges.
Need to check novelty before this filing date? Find Prior Art