解决牛鼻纹识别中未见个体误认问题，提升实际部署可靠性
Open-Set Cattle Muzzle Identification: A Leakage-Controlled Benchmark and Evaluation Protocol
- 将牛鼻识别建模为开集问题，支持新增个体不重训模型
- 引入防信息泄露评估协议，确保结果可复现且真实可靠
- 验证了阈值校准与嵌入质量对系统稳定性至关重要
可靠的个体牛只识别有助于疾病监测、疫苗记录、育种管理与畜牧保险。尽管牛鼻具有稳定、非接触的生物特征，现有识别系统大多假设已知动物集合固定，限制了实际应用。本文将牛鼻生物识别重构为开集、基于图库的识别问题，可拒绝未见过的个体，并支持增量注册而无需模型重训练。提出基于身份互斥划分、每折重训练、预留阈值校准、去重验证与自助置信区间的一套防泄漏评估协议。在两种嵌入配置下评估：混合CNN-ViT度量学习模型与MegaDescriptor-L基础模型。在理想阈值下，混合模型在10⁻¹、10⁻²、10⁻³误接受率目标下分别达到98.3%、96.4%、93.6%的检出与识别率；MegaDescriptor-L则分别为99.3%、98.1%、96.1%。但可部署的阈值校准后性能显著下降：混合模型在1%目标下误接受率为1.03%，而MegaDescriptor-L达2.44%。增量注册仅用一张参考图像即可实现91%以上排名1准确率，八张时最高达97.3%，且不影响原有图库性能。结果表明，阈值校准、防泄漏控制与嵌入质量是实现可靠开集牛只识别的关键，也为部署导向的动物生物识别系统提供了实用评估框架。
原文摘要 · Abstract (English)
Reliable individual cattle identification supports disease surveillance, vaccination records, breeding management, and livestock insurance. Although the bovine muzzle provides a stable, non-contact biometric, existing muzzle-recognition systems largely assume a closed set of enrolled animals, limiting their practical deployment. We reformulate cattle muzzle biometrics as an open-set, gallery-based identification problem that can reject previously unseen animals and support incremental enrollment without model retraining. We introduce a leakage-controlled evaluation protocol based on identity-disjoint splits, per-fold retraining, held-out threshold calibration, verified duplicate removal, and bootstrap confidence intervals. We evaluate the framework using two contrasting embedding configurations: a hybrid CNN-ViT metric-learning model and the MegaDescriptor-L foundation model. Under oracle threshold selection, the hybrid model achieves detection-and-identification rates of 98.3%, 96.4%, and 93.6% at target false-acceptance rates of 10^(-1), 10^(-2), and 10^(-3), respectively, while MegaDescriptor-L achieves 99.3%, 98.1%, and 96.1%. However, deployable threshold calibration reveals a substantial difference between oracle and calibrated performance: the hybrid model achieves a false-acceptance rate of 1.03% at a 1% target, whereas MegaDescriptor-L reaches 2.44%. Incremental enrollment further achieves Rank-1 accuracy above 91% with a single reference image and up to 97.3% with eight reference images, without retraining the model or degrading the existing gallery. These results demonstrate that threshold calibration, leakage control, and embedding quality are critical for reliable open-set cattle identification and provide a practical evaluation framework for deployment-oriented animal biometric systems.
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。