首页 > 论文 > 激光与光电子学进展 > 57卷 > 22期(pp:221019--1)

基于Fire Module 卷积神经网络的手写变造数字检测

Forgery Numeral Handwriting Detection Based on Fire Module Convolutional Neural Network

  • 摘要
  • 论文信息
  • 参考文献
  • 被引情况
  • PDF全文
分享:

摘要

提出基于卷积神经网络(CNN)的手写变造数字检测方法,为变造文件鉴定提供智能化解决方案。实验召集50名志愿者,采集50种不同品牌型号中性笔,形成6类变造笔迹和正常笔迹图像样本,建立了共计7200余份的样本数据。在AlexNet基础上引入Fire Module结构,提出基于变造数字检测的卷积神经网络(FNNet),以1×1卷积核代替部分3×3卷积核,实行卷积层组装来检测变造样本。实验结果表明,FNNet在6类手写变造数字中的平均测试准确率达98.36%,比AlexNet高3.01个百分点。所提方法优于传统特征分类器,为变造笔迹鉴定提供了一种新的方法。

Abstract

In this paper, we propose a method of forgery numeral handwriting detection based on convolution neural network (CNN). It provides an intelligent solution for forgery document detection. The experiment convened 50 volunteers and collected image samples of six types of forged handwritings and normal handwriting with 50 different brand pens, and established a total of more than 7200 sample data. Then, we designed a new CNN for forgery numeral handwriting detection called FNNet by introducing Fire Module structure based on AlexNet. We replaced the partial 3×3 convolution kernel with 1×1 convolution kernel and performed convolution layer assembly to detect forged samples. The experimental results show that the average test accuracy of FNNet in the six types of handwritten forgery numbers is 98.36%, which is 3.01 percentage higher than that of AlexNet. The proposed method is superior to traditional feature classifiers; it provides a new method for forged handwriting detection.

广告组1 - 空间光调制器+DMD
补充资料

中图分类号:TP391

DOI:10.3788/LOP57.221019

所属栏目:图像处理

基金项目:公安部刑事技术双十计划重点攻关项目、2018年上海市现场物证重点实验室开放课题基金;

收稿日期:2020-02-27

修改稿日期:2020-04-27

网络出版日期:2020-11-01

作者单位    点击查看

陈颖:中国人民公安大学刑事科学技术学院, 北京 100038
高树辉:中国人民公安大学刑事科学技术学院, 北京 100038

联系人作者:高树辉(gaoshuhui@ppsuc.edu.cn)

备注:公安部刑事技术双十计划重点攻关项目、2018年上海市现场物证重点实验室开放课题基金;

【1】Throckmorton G J. Disappearing ink: its use, abuse, and detection [J]. Journal of Forensic Sciences. 1990, 35(1): 12820J.Throckmorton G J. Disappearing ink: its use, abuse, and detection [J]. Journal of Forensic Sciences. 1990, 35(1): 12820J.

【2】Harris J. Developments in the analysis of writing inks on questioned documents [J]. Journal of Forensic Sciences. 1992, 37(2): 13269J.Harris J. Developments in the analysis of writing inks on questioned documents [J]. Journal of Forensic Sciences. 1992, 37(2): 13269J.

【3】Reed G, Savage K, Edwards D, et al. Hyperspectral imaging of gel pen inks: an emerging tool in document analysis [J]. Science & Justice. 2014, 54(1): 71-80.

【4】Megahed A, Fadl S M, Han Q, et al. Handwriting forgery detection based on ink colour features . [C]∥2017 8th IEEE International Conference on Software Engineering and Service Science (ICSESS), November 24-26, 2017, Beijing, China. New York: IEEE. 2017, 141-144.

【5】Dansena P, Bag S, Pal R. Differentiating pen inks in handwritten bank cheques using multi-layer perceptron [M]. ∥Shankar B U, Ghosh K, Mandal D P, et al. Pattern recognition and machine intelligence. Lecture notes in computer science. Cham: Springer. 2017, 10597: 655-663.

【6】Fukushima K. Neocognitron: a self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position [J]. Biological Cybernetics. 1980, 36(4): 193-202.

【7】Krizhevsky A, Sutskever I. Lake Tahoe, Nevada, USA . New York: Curran Associates. 2012, 2012(1): 1097-1105.

【8】Szegedy C, Liu W, Jia Y Q, et al. Going deeper with convolutions . [C]∥2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 7-12, 2015, Boston, MA, USA. New York: IEEE. 2015, 1-9.

【9】Silver D, Huang A, Maddison C J, et al. Mastering the game of Go with deep neural networks and tree search [J]. Nature. 2016, 529(7587): 484-489.

【10】Yan S D, Gao S H, Tang Y Q, et al. Plier and scissor mark recognition based on convolutional neural network [J]. Science Technology and Engineering. 2019, 19(31): 227-232.
严圣东, 高树辉, 唐云祁, 等. 基于卷积神经网络的钳剪工具痕迹识别 [J]. 科学技术与工程. 2019, 19(31): 227-232.
Yan S D, Gao S H, Tang Y Q, et al. Plier and scissor mark recognition based on convolutional neural network [J]. Science Technology and Engineering. 2019, 19(31): 227-232.
严圣东, 高树辉, 唐云祁, 等. 基于卷积神经网络的钳剪工具痕迹识别 [J]. 科学技术与工程. 2019, 19(31): 227-232.

【11】Yang M J, Tang Y Q, Jiang X J. Research on shoe pattern recognition method based on convolutional neural network [J]. Laser & Optoelectronics Progress. 2019, 56(17): 171501.
杨孟京, 唐云祁, 姜晓佳. 基于卷积神经网络的鞋型识别方法研究 [J]. 激光与光电子学进展. 2019, 56(17): 171501.

【12】Li Z R, Wang K X, He X L, et al. Heel-strike event detection algorithm based on convolutional neural networks [J]. Laser & Optoelectronics Progress. 2019, 56(21): 211503.
李卓容, 王凯旋, 何欣龙, 等. 基于卷积神经网络的足跟着地事件检测算法 [J]. 激光与光电子学进展. 2019, 56(21): 211503.

【13】Abdel-Hamid O, Mohamed A R, Jiang H, et al. Convolutional neural networks for speech recognition [J]. IEEE/ACM Transactions on Audio, Speech, and Language Processing. 2014, 22(10): 1533-1545.

【14】Karpathy A, Toderici G, Shetty S, et al. Large-scale video classification with convolutional neural networks . [C]∥2014 IEEE Conference on Computer Vision and Pattern Recognition, June 23-28, 2014, Columbus, OH, USA. New York: IEEE. 2014, 1725-1732.

【15】Zhang W, Zhang H X. Classification of main components of textile fabrics based on convolutional neural network Journal of Zhejiang Sci-Tech University[J]. 0, 2019(1): 1-8.
张玮, 张华熊. 基于卷积神经网络的纺织面料主成分分类 浙江理工大学学报[J]. 0, 2019(1): 1-8.

【16】Jiang X J, Gao S H. Automatic classification of microscopic hair images based on improved convolutional neural network [J]. Laser & Optoelectronics Progress. 2019, 56(23): 231002.
姜晓佳, 高树辉. 基于改进卷积神经网络的毛发显微图像自动分类 [J]. 激光与光电子学进展. 2019, 56(23): 231002.

【17】Sainath T N, Mohamed A R, Kingsbury B, et al. Deep convolutional neural networks for LVCSR . [C]∥2013 IEEE International Conference on Acoustics, May 26-31, 2013, Vancouver, BC, Canada. New York: IEEE. 2013, 8614-8618.

【18】Glorot X, Bengio Y. Understanding the difficulty of training deep feedforward neural networks [J]. Journal of Machine Learning Research. 2010, 249-256.

【19】Iandola F N, Han S, Moskewicz M W, <0.5 MB model size[EB/OL], et al. -11-04)[2020-02-26] . https:∥arxiv. 2016, org/abs/1602: 07360.

引用该论文

Chen Ying,Gao Shuhui. Forgery Numeral Handwriting Detection Based on Fire Module Convolutional Neural Network[J]. Laser & Optoelectronics Progress, 2020, 57(22): 221019

陈颖,高树辉. 基于Fire Module 卷积神经网络的手写变造数字检测[J]. 激光与光电子学进展, 2020, 57(22): 221019

您的浏览器不支持PDF插件,请使用最新的(Chrome/Fire Fox等)浏览器.或者您还可以点击此处下载该论文PDF