用对比学习检测选票笔迹是否出自同一人，准确率超现有方法。
MarkMatch: Same-Hand Stuffing Detection
- 基于对比学习，通过批量负样本提升对笔迹差异的感知能力。
- 在真实数据上达到0.943的F1分数，显著优于此前最优方法。
- 支持灵活标记提取，适合选举审计人员开展非生物特征核查。
我们提出MarkMatch，一种用于检测两张纸质选票笔迹是否由同一人书写的检索系统。与先前SOTA方法BubbleSig（仅对孤立笔迹对进行二分类）不同，MarkMatch采用对比学习，对查询笔迹与数据库中的笔迹进行风格相似性排序。模型通过密集批次相似性矩阵和双重损失目标训练，每个样本在批次内与多个负样本对比，从而学习细微的书写差异，在书写变化和视觉噪声下仍具强泛化能力，同时对角线监督确保真匹配的高置信度。模型在测试中取得0.943的F1分数，超越BubbleSig的最佳表现。系统还集成Segment Anything Model，支持基于框或点提示的灵活标记提取。该工具为选举审计人员提供了实用的可视化、非生物特征调查手段。
原文摘要 · Abstract (English)
We present MarkMatch, a retrieval system for detecting whether two paper ballot marks were filled by the same hand. Unlike the previous SOTA method BubbleSig, which used binary classification on isolated mark pairs, MarkMatch ranks stylistic similarity between a query mark and a mark in the database using contrastive learning. Our model is trained with a dense batch similarity matrix and a dual loss objective. Each sample is contrasted against many negatives within each batch, enabling the model to learn subtle handwriting difference and improve generalization under handwriting variation and visual noise, while diagonal supervision reinforces high confidence on true matches. The model achieves an F1 score of 0.943, surpassing BubbleSig's best performance. MarkMatch also integrates Segment Anything Model for flexible mark extraction via box- or point-based prompts. The system offers election auditors a practical tool for visual, non-biometric investigation of suspicious ballots.
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。