Signatures recognition based on strokes 3 D depth feature

Kun-shuai WU; Zhong-hui WEI; Xin HE; Pei-jun LI

doi:10.3788/YJYXS20193410.1013

您当前的位置：

首页 >

文章列表页 >

Signatures recognition based on strokes 3 D depth feature

Image Processing | 更新时间：2020-08-12

- Signatures recognition based on strokes 3 D depth feature
- Chinese Journal of Liquid Crystals and Displays Vol. 34, Issue 10, Pages: 1013-1020(2019)
- 作者机构：
  
  1.中国科学院长春光学精密机械与物理研究所, 吉林长春 130033
  2.中国科学院大学, 北京 100049
  3.中国人民解放军 63850部队, 吉林白城 137000
- 作者简介：
- 基金信息：
- DOI：10.3788/YJYXS20193410.1013
  CLC： TP391.4
- Received：06 June 2019，
  
  Accepted：21 August 2019，
  
  Published：05 October 2019
- 稿件说明：
移动端阅览
Kun-shuai WU, Zhong-hui WEI, Xin HE, et al. Signatures recognition based on strokes 3 D depth feature[J]. Chinese journal of liquid crystals and displays, 2019, 34(10): 1013-1020.
DOI：

Kun-shuai WU, Zhong-hui WEI, Xin HE, et al. Signatures recognition based on strokes 3 D depth feature[J]. Chinese journal of liquid crystals and displays, 2019, 34(10): 1013-1020. DOI： 10.3788/YJYXS20193410.1013.

摘要

针对熟练伪造签名识别正确率较低的问题，提出了基于笔划三维深度特征的个人签名识别方案。首先采集不同书写者的真实签名及他人的套摹签名，用高精度的体式显微镜分别对签名笔划进行扫描，获取签名笔划的表面三维点云数据。然后通过高斯滤波器滤掉三维点云数据中的噪声，计算签名笔划的平均深度、沿笔划方向深度标准差以及熵等统计特征。之后，对数据集进行数据增强，增加签名数据的数量。最后，将签名数据分为训练集和测试集，在不同训练比例下使用分类器（包括SVM、KNN、ANN）进行分类。实验结果显示，本文算法在本地签名数据集上的最佳识别正确率为98.69%，优于大多数传统算法，满足实际应用的要求。

Abstract

In order to solve the problem that the recognition rates of skilled forgery signatures is not satisfied

a personal signatures recognition scheme based on 3D depth feature of strokes is proposed. Firstly

the real signatures of different writers and the skilled forgery signatures are collected by high-precision stereo microscope

obtaining the surface 3D point cloud data of the signature strokes. Secondly

after filtering the noise of cloud data through the Gaussian filter

the statistical features such as the average depth of the stroke

the standard deviation of the depth along the stroke direction

and the entropy are calculated. To increase the number of data sets

data augmentation is implemented. Finally

the data set is divided into training set and test set

using classifier (including SVM

KNN

ANN) to classify the data set under different training ratios. The experimental results show that the best recognition accuracy of the algorithm on the local signature data set is 98.69%

which is better than most traditional algorithms and meets the requirements of practical applications.

关键词

Keywords

references

FERRER M A, VARGAS J F, MORALES A, et al . Robustness of offline signature verification based on gray level features[J]. IEEE Transactions on Information Forensics and Security , 2012, 7(3): 966-977.

OKAWA M. Offline signature verification based on bag-of-visualwords model using KAZE features and weighting schemes[C]// Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition Workshops . Las Vegas, NV, USA: IEEE, 2016: 252-258.

OKAWA M. From BoVW to VLAD with KAZE features: offline signature verification considering cognitive processes of forensic experts[J]. Pattern Recognition Letters , 2018, 113: 75-82.

CUIW C, GUO X P, SHAO H, et al . Offline Chinese signature verification based on AlexNet[C]// Proceedings of the 1 st International Conference on Advanced Hybrid Information Processing . Harbin, China: Springer, 2017: 33-37.

丁一, 詹恩奇, 郑建彬, 等.基于改进SIFT的离线签名鉴别方法[J].计算机应用研究, 2017, 34(11):3451-3454, 3462.

DING Y, ZHAN E Q, ZHENG J B, et al . Offline signature identification based on improved SIFT[J]. Application Research of Computers , 2017, 34(11): 3451-3454, 3462. (in Chinese)

MAERGNER P, PONDENKANDATH V, ALBERTI M, et al . Offline signature verification by combining graph edit distance and triplet networks[C]// Proceedings of 2018 Joint IAPR International Workshops on Statistical Techniques in Pattern Recognition (SPR) and Structural and Syntactic Pattern Recognition . Beijing, China: Springer, 2018: 470-480.

祖丽皮亚·艾尼.基于统计特征的维吾尔文离线手写签名鉴别技术研究[D].乌鲁木齐: 新疆大学, 2017.

GHENI Z. Study on Uyghur off-line handwritten signature verification based on statistical features[D]. Urumqi: XinJiang University, 2017. (in Chinese)

ZHANG S J, MAHPIRAT, AYSA Y, et al . BOVW based feature selection for Uyghur offline signature verification[C]// Proceedings of the 13 th Chinese Conference on Biometric Recognition . Urumqi, China: Springer, 2018: 700-708.

ZOIS E N, ALEWIJNSE L, ECONOMOU G. Offline signature verification and quality characterization using poset-oriented grid features[J]. Pattern Recognition , 2016, 54: 162-177.

马小晴, 桑庆兵.基于LBP和深度学习的手写签名识别算法[J].量子电子学报, 2017, 34(1):23-31.

MA X Q, SANG Q B.Handwritten signature verification algorithm based on LBP and deep learning[J]. Chinese Journal of Quantum Electronics , 2017, 34(1): 23-31. (in Chinese)

ZHANG S L, Li F L. Off-line handwritten Chinese signature verification based on support vector machine multiple classifiers[M]//HU W S. Advances in Electric and Electronics . Berlin, Heidelberg: Springer, 2012: 563-568.

JOSHI M A, GOSWAMI M M, ADESARA H H. Offline handwritten signature verification using low level stroke features[C]// Proceedings of 2015 International Conference on Advances in Computing , Communications and Informatics . Kochi, India: IEEE, 2015: 1214-1218.

FURUKAWA T. Detecting indentations on documents pressed by pen tip force using a near infrared light emitting diode (NIR LED) and shape from shading[C]// Proceedings of the 4th International Workshop on Computational Forensics . Tokyo, Japan: Springer, 2010: 114-125.

FURUKAWA T. The new method of identification of handwriting using volumes of indentations[C]// Proceedings of 2012 International Conference on Frontiers in Handwriting Recognition . Bari, Italy: IEEE, 2012: 163-168.

申思, 韩丹岩, 俞纲.运用笔迹三维信息提取分析仪对摹仿签名笔力特征的实验研究[J].中国刑警学院学报, 2016(3):66-69.

SHEN S, HAN D Y, YU G. Experimental study on the imitation signature pen-tip forces features using the handwriting 3D information extraction analyzer[J]. Journal of Criminal Investigation Police University of China , 2016(3): 66-69. (in Chinese)

凌剑勇, 何昕, 魏仲慧, 等.融合纹理特征与深度信息的足迹自动比对算法[J].光学精密工程, 2014, 22(7):1946-1954.

LING J Y, HE X, WEI Z H, et al . Footprint automatic alignment algorithm fusing texture features and depth information[J]. Optics and Precision Engineering , 2014, 22(7): 1946-1954. (in Chinese)

VARGAS J F, FERRER M A, TRAVIESO C M, et al . Off-line signature verification based on grey level information using texture features[J]. Pattern Recognition , 2011, 44(2): 375-385.

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

NCA-MobileNet： a lightweight facial expression recognition method

Semi-supervised spatial spectral local discriminant analysis for hyperspectral image feature extraction

Road object detection algorithm based on improved YOLOv5s

Adaptive ship target detection in complex background

Image super-resolution reconstruction network with dual attention and structural similarity measure

Related Author

HE Qiusheng

BAI Wushang

ZUO Yihai

HUANG Yucheng

LÜ Huanhuan

ZHANG Hui

WANG Yali

ZHOU Qing

Related Institution

School of Electronic Information Engineering， Taiyuan University of Science and Technology

Engineering Training Center， Taiyuan Institute of Technology

College of Software， Liaoning Technical University

College of Information Engineering， Huzhou University

School of Automation and Information Engineering， Sichuan University of Science & Engineering

AI问答

Address：No.3888 Dong Nanhu Road, Changchun, Jilin, China 130033 Postal code：130033
Tel：0431-86176059 Email：yjxs@ciomp.ac.cn
Technical support is provided by Beijing Founder electronics co., LTD 吉ICP备11002662号-17 京公网安备11010802024621
It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.

⁰