第二届身份证活体攻击检测竞赛，提升识别准确率但仍有挑战
Second Competition on Presentation Attack Detection on ID Card
- 设立自动评估平台与双赛道，分别评测算法与数据集
- 最佳团队在真实场景下达14.76%平均排名、6.36%错误率
- 适合身份认证、安防系统研究者参考
本文总结并报告了第二届身份证活体攻击检测竞赛的结果。相较于上届，本届新增三项改进：（1）启用自动评估平台实现自动化基准测试；（2）设立两个赛道，分别评估算法与数据集；（3）向赛道1团队提供新身份证数据集，作为训练优化的基准。德国达姆施塔特应用技术大学、弗劳恩霍夫IGD研究所与Facephi公司联合主办。共20支队伍注册，74个模型被评估。赛道1中，“Dragons”团队取得最高成绩，平均排名（AV-Rank）为40.48%，等错误率（EER）为11.44%。赛道2更具挑战性，“Incode”团队表现最优，AV-Rank达14.76%，EER为6.36%，相较首届比赛的74.30%和21.87%显著提升。结果表明，身份证活体攻击检测技术持续进步，但仍面临样本数量不足，尤其是正常图像稀缺的问题。
原文摘要 · Abstract (English)
This work summarises and reports the results of the second Presentation Attack Detection competition on ID cards. This new version includes new elements compared to the previous one. (1) An automatic evaluation platform was enabled for automatic benchmarking; (2) Two tracks were proposed in order to evaluate algorithms and datasets, respectively; and (3) A new ID card dataset was shared with Track 1 teams to serve as the baseline dataset for the training and optimisation. The Hochschule Darmstadt, Fraunhofer-IGD, and Facephi company jointly organised this challenge. 20 teams were registered, and 74 submitted models were evaluated. For Track 1, the "Dragons" team reached first place with an Average Ranking and Equal Error rate (EER) of AV-Rank of 40.48% and 11.44% EER, respectively. For the more challenging approach in Track 2, the "Incode" team reached the best results with an AV-Rank of 14.76% and 6.36% EER, improving on the results of the first edition of 74.30% and 21.87% EER, respectively. These results suggest that PAD on ID cards is improving, but it is still a challenging problem related to the number of images, especially of bona fide images.
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。