提出MMD滤波器，提升SIFT在指纹静脉识别中的匹配准确率
Robust Palm-Vein Recognition Using the MMD Filter: Improving SIFT-Based Feature Matching
- 通过均值和中位数距离筛选关键点，剔除错误匹配
- 在CASIA 850nm数据集上显著降低错误率
- 适合需要高精度的生物特征识别场景
手指或拇指的轻微移动、手部姿势变化会导致皮肤拉伸，使同一人产生无限多样的掌纹静脉图像。本文提出一种新的SIFT特征匹配滤波方法——均值与中位数距离（MMD）滤波器，通过计算关键点坐标的差异，在每个方向上求取均值和中位数，以剔除错误匹配。在CASIA数据集850nm子集上的实验表明，该方法能有效保留正确匹配点，同时减少其他滤波方法产生的误检。与现有基于SIFT的掌纹静脉识别系统相比，所提MMD滤波器表现出卓越性能，实现了更低的等错误率（EER）。本文为作者前期工作《一种基于SIFT的掌纹静脉识别关键点过滤方法》的扩展版本。
原文摘要 · Abstract (English)
A major challenge with palm vein images is that slight movements of the fingers and thumb, or variations in hand posture, can stretch the skin in different areas and alter the vein patterns. This can result in an infinite number of variations in palm vein images for a given individual. This paper introduces a novel filtering technique for SIFT-based feature matching, known as the Mean and Median Distance (MMD) Filter. This method evaluates the differences in keypoint coordinates and computes the mean and median in each direction to eliminate incorrect matches. Experiments conducted on the 850nm subset of the CASIA dataset indicate that the proposed MMD filter effectively preserves correct points while reducing false positives detected by other filtering methods. A comparison with existing SIFT-based palm vein recognition systems demonstrates that the proposed MMD filter delivers outstanding performance, achieving lower Equal Error Rate (EER) values. This article presents an extended author's version based on our previous work, A Keypoint Filtering Method for SIFT based Palm-Vein Recognition.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。