人工智能在手写签字鉴定应用中的研究

信息安全研究 ›› 2020, Vol. 6 ›› Issue (7): 622-633.

人工智能在手写签字鉴定应用中的研究

张行

中国金融认证中心 CFCA

收稿日期:2020-07-05 出版日期:2020-07-05 发布日期:2020-07-05
通讯作者: 张行
作者简介:张行中国金融认证中心（CFCA）副总经理，主要研究方向为电子认证、电子合同、电子支付领域的研究和应用。 zhangxing@cfca.com.com

A Perspective Analysis of Artificial Intelligence for Handwritten Signature Verification

Received:2020-07-05 Online:2020-07-05 Published:2020-07-05

摘要/Abstract

摘要： 手写签字鉴定自古以来都是鉴别身份得主要生物特征之一，尤其是在司法领域合同、票据等文书的鉴定方面有着举足轻重的地位。在信息化和移动互联网的发展浪潮中，电子化的合同应用已呈现出巨大潜力愈加流行，手写签字的形式及其应用也在发生着较大的变化，与此同时人工智能技术的发展也深刻地影响着计算机签字鉴定系统的技术路线，深度卷积神经网络CNN和深度循环递归神经网络RNN已被证明在大部分签字鉴定场景下均优于传统算法模型，本文将介绍计算机签字鉴定技术的基本原理及人工智能技术在此领域的前沿研究。

关键词: 人工智能, 手写签字, 离线签字, 在线签字, 神经网络, 签字鉴定

Abstract: Handwritten signature verification has been one of the main biometric identification since ancient times, especially in the verification of contracts, bills and other documents in the judicial field. As the rapid development of information technology and mobile Internet, electronic contract has shown its potential and becoming more and more popular, and the form and application of handwritten signatures have changed a lot. Meanwhile, the computer system of handwritten signature verification has been greatly improved by the artificial intelligence technology, the deep convolutional neural network CNN and deep recurrent neural network RNN have been proved to be superior to the traditional algorithm in most scenarios. This article will introduce the basic principles of computer system of handwritten signature verification and the cutting-edge application of artificial intelligence technology in this field.

Key words: Artificial Intelligence, Handwritten Signature, On-Line Signature, Off-Line Signature, Signature Verification

张行. 人工智能在手写签字鉴定应用中的研究[J]. 信息安全研究, 2020, 6(7): 622-633.

参考文献

[1] 张宁. 浅谈签名笔迹鉴定[J]. 广东公安科技, 2010, 3: 73~75 [2] 刘红. 签名笔迹的鉴定[J]. 云南公安高等专科学校学报, 2002, 2: 77~79 [3] Kalera M K, Srihari S, Xu A. Offline signature verification and identification using distance statistics[J]. International Journal of Pattern Recognition and Artificial Intelligence, 2004, 18(07): 1339-1360 [4] Ferrer M A, Diaz-Cabrera M, Morales A. Synthetic off-line signature image generation[C]//2013 international conference on biometrics (ICB). IEEE, 2013: 1-7 [5] Pal S, Alaei A, Pal U, et al. Performance of an off-line signature verification method based on texture features on a large indic-script signature dataset[C]//2016 12th IAPR Workshop on Document Analysis Systems (DAS). IEEE, 2016: 72-77 [6] Fierrez J, Galbally J, Ortega-Garcia J, et al. BiosecurID: a multimodal biometric database[J]. Pattern Analysis and Applications, 2010, 13(2): 235-246 [7] Ortega-Garcia J, Fierrez-Aguilar J, Simon D, et al. MCYT baseline corpus: a bimodal biometric database[J]. IEE Proceedings-Vision, Image and Signal Processing, 2003, 150(6): 395-401 [8] Lu X, Fang Y, Kang W, et al. SCUT-MMSIG: A multimodal online signature database[C]//Chinese Conference on Biometric Recognition. Springer, Cham, 2017: 729-738 [9] M. Antal, L. Z. Szabo, and T. Tordai, “Online signature verification on ´ MOBISIG finger-drawn signature corpus,” Mobile Information Systems, vol. 2018, 2018 [10] S. Dey, A. Dutta, J. I. Toledo, et al. “Signet: Convolutional siamese network for writer independent offline signature verification,” 2017. 1, 2, 4 [11] Pinzón-Arenas J O, Jiménez-Moreno R, Pachón-Suescún C G. Offline signature verification using DAG-CNN[J]. International Journal of Electrical & Computer Engineering 2019, 9 :2088-8708 [12] Sam S M, Kamardin K, Sjarif N N A, et al. Offline Signature Verification using Deep Learning Convolutional Neural Network (CNN) Architectures GoogLeNet Inception-v1 and Inception-v3[J]. Procedia Computer Science, 2019, 161: 475-483 [13] Masoudnia S, Mersa O, Araabi B N, et al. Multi-Representational Learning for Offline Signature Verification using Multi-Loss Snapshot Ensemble of CNNs[J]. Expert Systems with Applications, 2019, 133: 317-330 [14] Zagoruyko S, Komodakis N. Learning to compare image patches via convolutional neural networks[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2015: 4353-4361 [15] Li Chuang, Lin Feng, Wang Zhiyong, et al. DeepHSV: User-Independent Offline Signature Verification Using Two-Channel CNN[C]//2019 International Conference on Document Analysis and Recognition (ICDAR). IEEE, 2019: 166-171 [16] Lai S, Jin L, Yang W. Online signature verification using recurrent neural network and length-normalized path signature descriptor[C]//2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR). IEEE, 2017, 1: 400-405 [17] Rokui J. Autoassociative Signature Authentication Based on Recurrent Neural Network[C]//International Conference on Artificial Intelligence and Soft Computing. Springer, Cham, 2018: 88-96 [18] Tolosana R, Vera-Rodriguez R, Fierrez J, et al. Exploring recurrent neural networks for on-line handwritten signature biometrics[J]. Ieee Access, 2018, 6: 5128-5138 [19] Ahrabian K, BabaAli B. Usage of autoencoders and Siamese networks for online handwritten signature verification[J]. Neural Computing and Applications, 2019, 31(12): 9321-9334 [20] Li Chuang, Zhang Xing, Lin Feng, et al. A Stroke-Based RNN for Writer-Independent Online Signature Verification[C]//2019 International Conference on Document Analysis and Recognition (ICDAR). IEEE, 2019: 526-532