基于对抗生成网络的瓷砖纹理生成与防伪溯源  

Designs of Ceramic Patterned Tiles and Copyright Authentication Base on Generative Adversarial Framework

作　　者：赵怡 李俊 韩文 许康康 吴丽丹 王辉 徐为兵 ZHAO Yi;LI Jun;HAN Wen;XU Kangkang;WU Lidan;WANG Hui;XU Weibin(Jingdezhen Ceramic University,Jingdezhen 333403,Jiangxi,China;Ceramic Research Institute of Light Industry of China,Jingdezhen 333001,Jiangxi,China;Jingdezhen Oceano Ceramic Co.,Ltd,Jingdezhen 333000,Jiangxi,China)

机构地区：[1]景德镇陶瓷大学,江西景德镇333403 [2]中国轻工业陶瓷研究所,江西景德镇333001 [3]景德镇欧神诺陶瓷有限公司,江西景德镇333000

出　　处：《陶瓷学报》2024年第2期360-365,共6页Journal of Ceramics

基　　金：景德镇市陶瓷产业重大产学研协同攻关和成果转化项目(2023ZDGC003)。

摘　　要：由于移动电子设备发展迅速,知名品牌瓷砖产品上的设计图案容易被翻拍并仿造,给品牌带来经济损失。为实现对瓷砖纹理图像所属版权信息进行认证,提出一种基于对抗生成网络的防伪溯源框架。该框架将防伪信息直接转换成瓷砖纹理图像;从生成的纹理图像中可以提取出防伪信息,且防伪信息在视觉上不可见。生成的数字纹理图像在被打印、翻拍后,仍然能够从其中正确地提取出版权信息。实验表明:含防伪信息的瓷砖图像打印后再进行拍摄,解码率可以达到93%。提出的框架为瓷砖产品版权保护提供了一种新方法。Due to the rapid development of mobile electronic devices,the design patterns on well-known brand ceramic tile products are prone to being photographed and counterfeited,causing economic losses to the brands.In order to authenticate the copyright information of ceramic tile texture images,a copyright anti-counterfeiting authentication framework based on generative adversarial networks is proposed.This framework converts copyright information into ceramic tile texture images,from which the copyright information can be extracted and visually imperceptible.The generated digital texture images can still correctly extract copyright information even after being printed and photographed.It is experimentally showed that the decoding rate is as high as 93%when capturing images of ceramic tile patterns containing copyright information.Our framework is a new method for copyright protection of ceramic tile products.

关 键 词：瓷砖图像 版权认证 对抗生成式框架 

分 类 号：TQ174.75[化学工程—陶瓷工业]