发表机构
University of Surrey; Metropolitan Police UK（萨里大学; 英国大都会警察局）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出KnifeHunter系统及配套数据集，开发CoRe-Net架构实现细刀具图像检索，在评估中表现优异且已被英国警方实际部署应用。
AI 中文摘要
刀具暴力是重大公共安全挑战，执法机构需要可扩展工具用于刀具目录级识别、情报分析及来源归因。人工视觉比对专业度高、耗时且在操作成像条件下难以规模化。本文介绍与英国执法机构联合开发的端到端法医刀具图像检索系统KnifeHunter。该工作贡献了KnifeHunter数据集，包含来自警方证物、零售目录及边境缉获的543类刀具的25843张图像，配有结构化元数据、中/难评估协议及大规模干扰项评估。本文进一步提出CoRe-Net，一种紧凑的单描述符检索架构，结合全局上下文与空间局部判别证据；CoRe-Net引入结构化互补表示学习（SCRL）将局部证据组织为基于原型的互补表示，以及双向互逆融合（BDRF）通过残差投影与门控局部到全局注入整合全局与局部证据。使用EVA02-Base骨干网络与余弦相似度检索，CoRe-Net在Medium协议下达到88.0% mAP、86.7% mP@10，在干扰项条件下达到85.1% mAP、83.8% mP@10。KnifeHunter于2023至2025年在Operation Sceptre部署期间被英国警方使用，在现场查询中达到99.2% mP@1。这些结果证明了该框架是执法操作环境中实用且有效的细粒度法医刀具匹配多媒体检索框架。
英文摘要
Knife-enabled violence presents a major public safety challenge, and law enforcement agencies require scalable tools for catalogue-level knife identification, intelligence analysis, and source attribution. Manual visual comparison is specialist, time-consuming, and difficult to scale under operational imaging conditions. We introduce KnifeHunter, an end-to-end forensic knife image retrieval system developed with UK law enforcement. The work contributes the KnifeHunter dataset, comprising 25,843 images across 543 knife classes from police evidence, retail catalogues, and border-force seizures, with structured metadata, Medium/Hard evaluation protocols, and large-scale distractor evaluation. We further propose CoRe-Net, a compact single-descriptor retrieval architecture that combines global context with spatially localised discriminative evidence. CoRe-Net introduces Structured Complementary Representation Learning (SCRL) to organise local evidence into complementary prototype-based representations, and Bi-Directional Reciprocal Fusion (BDRF) to integrate global and local evidence through residual projection and gated local-to-global injection. Using an EVA02-Base backbone and cosine-similarity retrieval, CoRe-Net achieves 88.0% mAP and 86.7% mP@10 on the Medium protocol, and 85.1% mAP and 83.8% mP@10 under distractor conditions. KnifeHunter was deployed by UK police forces during Operation Sceptre deployments from 2023 to 2025, achieving 99.2% mP@1 on field queries. These results demonstrate a practical and effective multimedia retrieval framework for fine-grained forensic knife matching in operational law-enforcement settings.
