基于ASIFT的离线签名认证方法

唐有宝; 卜巍; 张恩泽; 邬向前

doi:10.13700/j.bh.1001-5965.2014.0453

基于ASIFT的离线签名认证方法

doi: 10.13700/j.bh.1001-5965.2014.0453

1.
哈尔滨工业大学计算机科学与技术学院, 哈尔滨 150001
2. 哈尔滨工业大学媒体技术与艺术系, 哈尔滨 150001
3. 哈尔滨工业大学航天学院, 哈尔滨 150001

基金项目: 国家自然科学基金资助项目(61073125,61350004);中央高校基本科研业务费专项资金资助项目(HIT.NSRIF.2013091,HIT.HSS.201407)

详细信息

作者简介:
唐有宝(1987-),男,湖南衡阳人,博士生,tangyoubao@hit.edu.cn

通讯作者:
卜巍(1977-),男,黑龙江哈尔滨人,讲师,buwei@hit.edu.cn,主要研究方向为图像处理、模式识别、数字艺术设计.

中图分类号: TP391.4
计量
- 文章访问数: 1224
- HTML全文浏览量: 132
- PDF下载量: 659
- 被引次数: 0
出版历程
- 收稿日期: 2014-04-28
- 网络出版日期: 2015-01-20

Offline signature verification based on ASIFT

1.
School of Computer Science and Technology, Harbin Institute of Technology, Harbin 150001, China
2. Department of New Media Technologies and Arts, Harbin Institute of Technology, Harbin 150001, China
3. School of Astronautics, Harbin Institute of Technology, Harbin 150001, China

摘要

摘要: 通过分析现有局部不变特征方法及含伪装签名数据集的特点,提出了一种基于具有仿射不变性的尺度不变特征变换(ASIFT)的离线签名认证方法.该方法对签名图像进行预处理(包括灰度化和放缩),对处理后的图像进行ASIFT关键点检测和特征描述符提取,对从查询签名图像和参考签名图像中提取到的描述符进行匹配,对匹配的结果采用随机采样一致性(RANSAC)方法去掉错误匹配,并计算正确匹配点的描述符之间的平均距离;通过比较平均距离及正确匹配点的个数与给定阈值的大小来判断认证是否成功.使用了含伪装签名的数据库对提出的方法进行测试,实验结果表明该方法与现有方法相比等误率降低了5%.
- 离线签名认证 /
- 伪装签名 /
- 局部特征 /
- 仿射且尺度不变特征变换 /
- 随机采样一致性
Abstract: A novel offline signature verification method based on the affine and scale invariant feature transform (ASIFT) was proposed by analyzing the existing local invariant features and the property of the disguised signature. The method consists of the following steps, the preprocessing including image graying and resizing was performed on the signature images; the key points were detected and the corresponding descriptors were extracted from the processed images; the descriptors extracted from the query and reference images were matched and the random sample consensus (RANSAC) algorithm was used to refine the matched result. Then the average distance was computed according to the distances between the descriptors of the correct matched points. The verification decision was given by comparing the average distance and the number of the correct matched points with the thresholds. The proposed method was evaluated on a public signature dataset including the disguised signatures and the experimental results show that the proposed method outperforms the state-of-the-art algorithms with reducing the equal error rate (EER) by 5%.
- offline signature verification /
- disguised signature /
- local feature /
- affine and scale invariant feature transform (ASIFT) /
- random sample consensus (RANSAC) algorithm

HTML全文

参考文献(28)

[1]	Liwicki M,Heuvel C E,Found B,et al.Forensic signature verification competition 4NSigComp2010-detection of simulated and disguised signatures[C]//Proceedings of the International Conference on Frontiers in Handwriting Recognition.Piscataway,NJ:IEEE,2010:715-720.
[2]	Lowe D.Distinctive image features from scale-invariant keypoints[J].International Journal of Computer Vision,2004,60(2):91-110.
[3]	Alahi A,Ortiz R,Vandergheynst P.FREAK:fast retina keypoint[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Piscataway,NJ:IEEE,2012:510-517.
[4]	Fischler M,Bolles R.Random sample consensus:a paradigm for model fitting with aplications to image analysis and automated cartography[J].Commun ACM,1981,24(6):381-395.
[5]	Wu X Q,Tang Y B,Bu W.Offline text-independent writer identification based on scale invariant feature transform[J].IEEE Transactions on Information Forensics and Security,2014,9(3):526-536.
[6]	Morel J M,Yu G S.ASIFT:a new framework for fully affine invariant image comparison[J].SIAM Journal on Imaging Sciences,2009,2(2):438-469.
[7]	Chen S Y,Srihari S.Use of exterior contours and shape features in off-line signature verification[C]//Proceedings of the International Conference on Document Analysis and Recognition.Piscataway,NJ:IEEE,2005:1280-1284.
[8]	Alekseev K V,Egorova S D.Handwritten signature verification based on code representation[J].Pattern Recognition and Image Analysis,2007,17(4):487-492.
[9]	Fang B,Chen W S,You X G,et al.Wavelet thinning algorithm based similarity evaluation for offline signature verification[C]//Proceedings of the International Conference on Intelligent Computing.New York:Springer,2006:547-555.
[10]	Hanmandlu M,Yusof M H M,Madasu V K.Off-line signature verification and forgery detection using fuzzy modeling[J].Pattern Recognition,2005,38(3):341-356.
[11]	Impedovo D,Pirlo G.Automatic signature verification: the state of the art[J].IEEE Transactions on Systems,Man,and Cybernetics,Part C:Applications and Reviews,2008,38(5):609-635.
[12]	Blankers V L,Heuvel C,Franke K Y,et al.ICDAR 2009 signature verification competition[C]//Proceedings of the International Conference on Document Analysis and Recognition.Piscataway,NJ:IEEE,2009:1403-1407.
[13]	Blumenstein M,Ferrer M A,Vargas J F.The 4NSigComp2010 off-line signature verification competition: scenario 2[C]//Proceedings of the International Conference on Frontiers in Handwriting Recognition.Piscataway, NJ:IEEE,2010:721-726.
[14]	Liwicki M,Malik M I,van den Heuvel C E,et al.Signature verification competition for online and offline skilled forgeries (SigComp2011)[C]//Proceedings of the International Conference on Document Analysis and Recognition.Piscataway,NJ:IEEE,2011:1480-1484.
[15]	Liwicki M,Malik M I,Alewijnse L,et al.ICFHR 2012 competition on automatic forensic signature verification (4NsigComp 2012)[C]//Proceedings of the International Conference on Frontiers in Handwriting Recognition.Piscataway,NJ:IEEE,2012:823-828.
[16]	Malik M I,Liwicki M,Alewijnse L,et al.ICDAR 2013 competitions on signature verification and writer identification for on- and offline skilled forgeries(SigWiComp 2013)[C]//Proceedings of the International Conference on Document Analysis and Recognition.Piscataway,NJ:IEEE,2013:1477-1483.
[17]	Porwik P,Para T.Some handwritten signature parameters in biometric recognition process[C]//Proceedings of the International Conference on Information Technology Interfaces.Piscataway,NJ:IEEE,2007:185-190.
[18]	Lv H R,Wang W Y,Wang C,et al.Off-line Chinese signature verification based on support vector machines[J].Pattern Recognition Letters,2005,26(15):2390-2399.
[19]	Shridhar M,Houle G,Bakker R,et al.Real-time feature-based automatic signature verification[C]//Proceedings of the International Workshop on Frontiers in Handwriting Recognition.Piscataway,NJ:IEEE,2006.
[20]	Zuo W M,Li S F,Zeng X G.A hybrid scheme for off-line Chinese signature verification[C]//Proceedings of the IEEE Conference on Cybernetics and Intelligent Systems.Piscataway,NJ:IEEE,2004:1402-1405.
[21]	Chen G Y,Kegl B.Invariant radon-wavelet packet signatures for pattern recognition[C]//Proceedings of the Canadian Conference on Electrical and Computer Engineering.Piscataway,NJ:IEEE,2006:1471-1474.
[22]	Fasquel J B,Bruynooghe M.A hybrid opto-electronic method for fast off-line handwritten signature verification[J].International Journal on Document Analysis and Recognition,2004,7(1):56-68.
[23]	Oliveira L,Justino E,Sabourin R.Off-line signature verification uing writer-independent approach[C]//Proceedings of the International Joint Conference on Neural Networks.Piscataway,NJ:IEEE,2007:2539-2544.
[24]	Armand S,Blumenstein M,Muthukkumarasamy V.Off-line signature verification based on the modified direction feature[C]//Proceedings of the International Conference on Pattern Recognition.Piscataway,NJ:IEEE,2006:509-512.
[25]	Vu N,Blumenstein M,Muthukkumarasamy V,et al.Off-line signature verification using enhanced modified direction features in conjunction with neural classifiers and support vector machines[C]//Proceedings of the International Conference on Document Analysis and Recognition.Piscataway,NJ:IEEE,2007:734-738.
[26]	Malik M,Liwicki M,Dengel A.Local features for forensic signature verification[C]//Proceedings of the International Conference on Image Analysis and Processing.New York:Springer,2013:103-111.
[27]	Fang B,Leung C H,Tang Y Y,et al.Off-line signature verification by the tracking of feature and stroke positions[J].Pattern Recognition,2003,36(1):91-101.
[28]	Malik M I,Ahmed S,Liwicki M,et al.FREAK for real time forensic signature verification[C]//Proceedings of the International Conference on Document Analysis and Recognition.Piscataway,NJ:IEEE,2013:971-975