Multi-Path Attention Inverse Discrimination Network for Offline Signature Verification  

作　　者：Xiaorui Zhang Yingying Wang Wei Sun Qi Cui Xindong Wei 

机构地区：[1]School of Computer and Software,Nanjing University of Information Science&Technology,Nanjing,210044,China [2]Wuxi Research Institute,Nanjing University of Information Science&Technology,Wuxi,214100,China [3]Engineering Research Center of Digital Forensics,Ministry of Education,Jiangsu Engineering Center of Network Monitoring,Nanjing,210044,China [4]Jiangsu Collaborative Innovation Center of Atmospheric Environment and Equipment Technology(CICAEET),Nanjing University of Information Science&Technology,Nanjing,210044,China [5]School of Automation,Nanjing University of Information Science&Technology,Nanjing 210044,China [6]Department of Electrical and Computer Engineering,University of Windsor,Windsor,N9B 3P4,Canada [7]School of Teacher Education,Nanjing University of Information Science&Technology,Nanjing,210044,China

出　　处：《Intelligent Automation & Soft Computing》2023年第6期3057-3071,共15页智能自动化与软计算（英文）

基　　金：This work was supported,in part,by the National Nature Science Foundation of China under grant numbers 62272236;in part,by the Natural Science Foundation of Jiangsu Province under grant numbers BK20201136,BK20191401;in part,by the Priority Academic Program Development of Jiangsu Higher Education Institutions(PAPD)fund.

摘　　要：Signature verification,which is a method to distinguish the authenticity of signature images,is a biometric verification technique that can effectively reduce the risk of forged signatures in financial,legal,and other business envir-onments.However,compared with ordinary images,signature images have the following characteristics:First,the strokes are slim,i.e.,there is less effective information.Second,the signature changes slightly with the time,place,and mood of the signer,i.e.,it has high intraclass differences.These challenges lead to the low accuracy of the existing methods based on convolutional neural net-works(CNN).This study proposes an end-to-end multi-path attention inverse dis-crimination network that focuses on the signature stroke parts to extract features by reversing the foreground and background of signature images,which effectively solves the problem of little effective information.To solve the problem of high intraclass variability of signature images,we add multi-path attention modules between discriminative streams and inverse streams to enhance the discriminative features of signature images.Moreover,a multi-path discrimination loss function is proposed,which does not require the feature representation of the samples with the same class label to be infinitely close,as long as the gap between inter-class distance and the intra-class distance is bigger than the set classification threshold,which radically resolves the problem of high intra-class difference of signature images.In addition,this loss can also spur the network to explore the detailed infor-mation on the stroke parts,such as the crossing,thickness,and connection of strokes.We respectively tested on CEDAR,BHSig-Bengali,BHSig-Hindi,and GPDS Synthetic datasets with accuracies of 100%,96.24%,93.86%,and 83.72%,which are more accurate than existing signature verification methods.This is more helpful to the task of signature authentication in justice and finance.

关 键 词：Offline signatures biometric verification multi-path discrimination loss attention mechanisms inverse discrimination 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]