用手机拍的衣服照片，就能识别真假，无需特殊标签
Deep neural network-based detection of counterfeit products from smartphone images
- 仅靠手机拍摄的自然光照图像，用深度神经网络判断真伪
- 在首批测试品牌中准确率达99.71%，误判率3.06%
- 只需少量真假样品微调，可推广到药品、香水等品类
假药、疫苗以及高奢手袋、手表、珠宝、服饰和化妆品等假冒产品，给正规厂商带来巨大直接经济损失，也造成广泛社会成本。本文提出全球首个纯基于计算机视觉的防伪系统，无需产品添加特殊安全标签或修改供应链追踪方式。该深度神经网络系统在自然、弱控制环境下（如零售店、海关、仓库、户外）拍摄的知名品牌服装图像上表现优异，首次测试中准确率达99.71%，误判率3.06%。通过少量真伪样品微调后，该系统可拓展至时尚配饰、香水盒、药品等多个品类，具备广泛实用前景。
原文摘要 · Abstract (English)
Counterfeit products such as drugs and vaccines as well as luxury items such as high-fashion handbags, watches, jewelry, garments, and cosmetics, represent significant direct losses of revenue to legitimate manufacturers and vendors, as well as indirect costs to societies at large. We present the world's first purely computer-vision-based system to combat such counterfeiting-one that does not require special security tags or other alterations to the products or modifications to supply chain tracking. Our deep neural network system shows high accuracy on branded garments from our first manufacturer tested (99.71% after 3.06% rejections) using images captured under natural, weakly controlled conditions, such as in retail stores, customs checkpoints, warehouses, and outdoors. Our system, suitably transfer trained on a small number of fake and genuine articles, should find application in additional product categories as well, for example fashion accessories, perfume boxes, medicines, and more.
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。