Wang Po-Tong, Tseng Chiu Wang, Fang Li-Der
Department of Electrical Engineering, Lunghwa University of Science and Technology, Taoyuan 333326, Taiwan.
Department of Biomechatronics Engineering, National Taiwan University, Taipei 10617, Taiwan.
Sensors (Basel). 2024 Dec 28;25(1):128. doi: 10.3390/s25010128.
The proliferation of sophisticated counterfeiting poses critical challenges to global security and commerce, with annual losses exceeding $2.2 trillion. This paper presents a novel physics-constrained deep learning framework for high-precision security ink colorimetry, integrating three key innovations: a physics-informed neural architecture achieving unprecedented color prediction accuracy (CIEDE2000 (ΔE00): 0.70 ± 0.08, < 0.001), advanced attention mechanisms improving feature extraction efficiency by 58.3%, and a Bayesian optimization framework ensuring robust parameter tuning. Validated across 1500 industrial samples under varying conditions (±2 °C, 30-80% RH), this system demonstrates substantial improvements in production efficiency with a 50% reduction in rejections, a 35% decrease in calibration time, and 96.7% color gamut coverage. These achievements establish new benchmarks for security printing applications and provide scalable solutions for next-generation anti-counterfeiting technologies, offering a promising outlook for the future.
复杂伪造行为的激增给全球安全和商业带来了严峻挑战，每年造成的损失超过2.2万亿美元。本文提出了一种用于高精度安全油墨比色法的新型物理约束深度学习框架，集成了三项关键创新：一种物理知识引导的神经架构，实现了前所未有的颜色预测精度（CIEDE2000（ΔE00）：0.70±0.08，<0.001）；先进的注意力机制，将特征提取效率提高了58.3%；以及一个贝叶斯优化框架，确保稳健的参数调整。该系统在不同条件（±2°C，30-80%RH）下对1500个工业样本进行了验证，在生产效率方面有显著提高，废品率降低了50%，校准时间减少了35%，色域覆盖率达到96.7%。这些成果为安全印刷应用树立了新的标杆，并为下一代防伪技术提供了可扩展的解决方案，为未来提供了广阔的前景。
