Open AccessOptimized jk-nearest neighbor based online signature verification and evaluation of the main parameters
Author(s) -
Mohammad Saleem,
Bence Kővári
Publication year - 2021
Publication title -
computer science
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.145
H-Index - 5
eISSN - 2300-7036
pISSN - 1508-2806
DOI - 10.7494/csci.2021.22.4.4102
Subject(s) - computer science , k nearest neighbors algorithm , classifier (uml) , data mining , word error rate , signature (topology) , pattern recognition (psychology) , artificial intelligence , algorithm , mathematics , geometry
In this paper, we propose an enhanced jk-nearest neighbor (jk-NN) classifier for online signature verification. After studying the algorithm's main parameters, we use four separate databases to present and evaluate each algorithm parameter. The results show that the proposed method can increase the verification accuracy by 0.73-10% compared to a traditional one class k-NN classifier. The algorithm has achieved reasonable accuracy for different databases, a 3.93% error rate when using the SVC2004 database, 2.6% for MCYT-100 database, 1.75% for the SigComp'11 database, and 6% for the SigComp'15 database.The proposed algorithm uses specifically chosen parameters and a procedure to pick the optimal value for K using only the signer's reference signatures, to build a practical verification system for real-life scenarios where only these signatures are available. By applying the proposed algorithm, the average error achieved was 8% for SVC2004, 3.26% for MCYT-100, 13% for SigComp'15, and 2.22% for SigComp'11.