Innovative Outlier Removal Techniques to Enhance Signature Authentication Accuracy for Smart Society

A smart society is an empowered society, which can improve the lives of its citizens by using the latest innovations and technologies. This improvement can happen in several dimensions out of which security is a major one. Inconsistency and forgery are very common phenomenon where handwritten signatures are often preserved for training a classifier to authenticate a person. The removal of outliers, at the outset, obviously improves the quality of training and the classifier. The present article deals with the mechanized segregation of the poor-quality authentic signatures from reliable ones. Machine learning algorithms for outlier handling utilizing clustering, classification and statistical techniques have been implemented in this context. Subsequent performance evaluation after outlier removal reflects improvement of both true positive and true negative recognition rate accuracy. The performance evaluation presents the significant differences between authentication accuracy and forgery accuracy in the context of building a safe, secure and smart society.

[1]  Hong Yan,et al.  Off-line signature verification based on geometric feature extraction and neural network classification , 1997, Pattern Recognit..

[2]  Mayur C. Waghere.  Survey on Offline Handwritten Signature Verification , 2017 .

[3]  Shehzad Khalid,et al.  A Review of Offline Signature Verification Techniques , 2014 .

[4]  S. Imandoust,et al.  Application of K-Nearest Neighbor (KNN) Approach for Predicting Economic Events: Theoretical Background , 2013 .

[5]  Ben M. Herbst,et al.  Offline Signature Verification Using the Discrete Radon Transform and a Hidden Markov Model , 2004, EURASIP J. Adv. Signal Process..

[6]  N. Otsu.  A threshold selection method from gray level histograms , 1979 .

[7]  S. Venkata Lakshmi,et al.  Application of k-Nearest Neighbour Classification Method for Intrusion Detection in Network Data , 2014 .

[8]  H. Pourghassem,et al.  Signature Identification Using Dynamic and HMM Features and KNN Classifier , 2013, 2013 International Conference on Communication Systems and Network Technologies.

[9]  V. K. Bhuvaneswari,et al.  A Comparative Study of Various Clustering Algorithms in Data Mining , 2014 .

[10]  Chitrita Chaudhuri,et al.  Authentication of Offline Signatures Based on Central Tendency of Features and Dynamic Time Warping Values Preserved for Genuine Cases , 2014, 2014 Fourth International Conference of Emerging Applications of Information Technology.

[11]  Bulusu Lakshmana Deekshatulu,et al.  Classification of Heart Disease Using K- Nearest Neighbor and Genetic Algorithm , 2015, ArXiv.

[12]  G. Dimauro,et al.  A Multi-Expert Signature Verification System for Bankcheck Processing , 1997, Int. J. Pattern Recognit. Artif. Intell..

[13]  Haris Baltzakis,et al.  A new signature verification technique based on a two-stage neural network classifier , 2001 .

[14]  Mansoor Ahmed,et al.  Smart Cities: A Survey on Security Concerns , 2016 .

[15]  Thair Nu Phyu.  Survey of Classification Techniques in Data Mining , 2009 .

[16]  Shuchita Upadhyaya,et al.  Outlier Detection: Applications And Techniques , 2012 .

[17]  Pavel Berkhin,et al.  A Survey of Clustering Data Mining Techniques , 2006, Grouping Multidimensional Data.

[18]  Jarrod Trevathan,et al.  Neural Network-based Hwritten Signature Verification , 2008, J. Comput..