基于改进LPP和ECOC-SVMS的离线签名识别方法

doi:10.3969/j.issn.1006-2475.2018.10.015

计算机与现代化

基于改进LPP和ECOC-SVMS的离线签名识别方法

（湖南省妇幼保健院信息中心，湖南长沙410008）

收稿日期:2018-06-07 出版日期:2018-10-26 发布日期:2018-10-26
作者简介:蒋青云（1978-），男，江西吉安人，湖南省妇幼保健院信息中心工程师，硕士，研究方向：通信与信息系统。

Method of Off-line Signature Recognition Based on Improved LPP and ECOC-SVMS

(Information Center, Hunan Maternal and Child Health Care Center, Changsha 410008, China)

Received:2018-06-07 Online:2018-10-26 Published:2018-10-26

摘要/Abstract

摘要： 提出一种基于改进LPP和ECOC-SVMS的离线签名识别方法。针对预处理后的签名图像，选择多种有效特征构建高维特征向量，引入一种改进的保局投影方法进行特征提取并同时实现高效降维；签名识别方面，使用基于Hadamard纠错编码方法的ECOC支持向量机多类分类方法，并引入近似概率对ECOC解码进行改进，以提升多类分类器的性能。实验结果表明此方法的可行性和有效性。

关键词: 离线签名识别, 保局投影, 纠错编码支持向量机

Abstract: A method of off-line signature recognition based on locality preserving projection(LPP) and Error Correcting Output Code support vector machine(ECOC-SVMS) is proposed. After selecting multiple features from preprocessed signature images, high dimensionality feature vectors are constructed. Then, an improved LPP method is used to extract effect features and reduce dimensionality. A multi-classification classifier based on Hadamard code ECOC-SVMS is used to deal with signature recognition problem. A proximate probability output of SVMS is employed to improve the decoding processing of ECOC framework to enhance the performance of multi-classification. The experiment result shows that the proposed method is feasible and effective.

Key words: off-line signature recognition, locality preserving projection, error correcting output code support vector machine

中图分类号:

TP317.4

蒋青云. 基于改进LPP和ECOC-SVMS的离线签名识别方法[J]. 计算机与现代化, doi: 10.3969/j.issn.1006-2475.2018.10.015.

JIANG Qing-yun. Method of Off-line Signature Recognition Based on Improved LPP and ECOC-SVMS[J]. Computer and Modernization, doi: 10.3969/j.issn.1006-2475.2018.10.015.

参考文献

［1］蔺道志. 基于稀疏表达的离线签名笔迹鉴定研究［D］. 广州：中山大学， 2014.
［2］ VARGAS J F, FERROR M A, TRAVIESO C M, et al. Off-line signature verification based on gray level information using texture features［J］. Pattern Recognition, 2011,44(2):375-385.
［3］ FERRER M A, VARGAS J, 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.
［4］ JAISWAL S G, KASETWAR A R. Off-line signature verification using global & local features with neural networks［C］// Proceedings of 2014 International Conference on Advanced Communication Control and Computing Technologies. 2014:1525-1531.
［5］ SHEKAR B H, BHARATHI R K. DCT-SVM-Based Technique for Off-line Signature Verification［M］. Springer, 2014:843-853.
［6］ PHAM T A, LE H H, DO N T. Offline handwritten signature verification using local and global features［J］. Annals of Mathematics and Artificial Intelligence, 2015,75(1):231-247.
［7］ HATKAR P V, SALOKHE B T, MALGAVE A A. Offline handwritten signature verification using neural network［J］. Methodology, 2015,2(1):1-5.
［8］ SERDOUK Y, NEMMOUR H, CHIBANI Y. New off-line handwritten signature verification method based on artificial immune recognition system［J］. Expert Systems with Application, 2016,51(C):186-194.
［9］ DAS S, ROY A. Signature Verification Using Rough Set Theory Base Feature Selection［M］. Springer India, 2016:153-161.
［10］HE X F, NIYOGI P.Locality preserving projections［C］// Proceedings of Advances in Neural Information Processing System. 2004：153-160.
［11］赵振华,郝晓弘. 局部保持鉴别投影及其在人脸识别中的应用［J］. 电子与信息学报， 2013,35(2):463-467.
［12］LIU F Y,XIA K W,NIU W J. Improved reconstruction weight-based locally linear embedding algorithm［J］． Journal of Image and Graphics, 2018,23(1):52-60．
［13］刘方原，夏克文，牛文佳．改进重构权值的局部线性嵌入算法［J］．中国图象图形学报, 2018,23(1):52-60．
［14］PLATT J C. Probabilistic outputs for support vector machines and comparison to regularized likelihood methods［J］. Advances in Large Margin Classifiers, 2000,3(5):61-74.
［15］YIN A R, XIE X, KUANG J M. Application of Hadamard ECOC in multi-class problems based on SVM［J］. Acta Electronica Sinica, 2008,36(1):122-126.
［16］WANG Z Y, XU W R, GUO J. Using probability estimation via outputs of SVM in ECOC［J］. International Journal of Digital Content Technology and Its Applications, 2011,5(3):185-191.
［17］张洁玉,赵鸿萍,陈曙. 自适应阈值及加权局部二值模式的人脸识别［J］. 电子与信息学报, 2014,36(6):1327-1333.

[1]	肖文国1，葛华勇1,2，彭阳洋1. 基于模运算的彩色图像隐写算法[J]. 计算机与现代化, 2018, 0(10): 48-.
[2]	毕金强,许家帅,辛全波,尚东方. 一种基于SURF与地理格网模型的增强现实方法[J]. 计算机与现代化, 2018, 0(06): 47-.
[3]	李伟祥,李展,吴少春,邓福明. 基于超分重建技术的图像增强系统[J]. 计算机与现代化, 2014, 0(5): 94-98.
[4]	姜太平,陈雅娟. 基于DBBS模型的中间帧生成技术[J]. 计算机与现代化, 2014, 0(3): 85-88,93.
[5]	云静. H.264视频编码的关键技术分析及复杂度研究测试[J]. 计算机与现代化, 2010, 1(6): 51-0054.

基于改进LPP和ECOC-SVMS的离线签名识别方法

Method of Off-line Signature Recognition Based on Improved LPP and ECOC-SVMS

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 5

编辑推荐

Metrics

本文评价