AUNet: a deep learning method for spectral information classification to identify inks
Yan Shi, Xinyu He, Qinglun Zhang, Chongbo Yin, Ninghui Feng, Haoming Chen, Hualing Lin
Abstract
A U-shaped network with attention modules (AUNet) is proposed and combined with a hyperspectral system to effectively identify different inks. It provides an effective detection method for illegal tampering with documents.
Topics & Concepts
Artificial intelligenceComputer scienceDeep learningPattern recognition (psychology)Machine learningRemote-Sensing Image ClassificationCultural Heritage Materials AnalysisCurrency Recognition and Detection