Bio-Inspired Reference Level Assigned DTW for Person Identification Using Handwritten Signatures

Person identification or verification is becoming an important issue in our life with the growth of information technology. Handwriting features of individuals during signing are used as behavioral biometrics. This paper presents a new method for recognizing person using online signatures based on reference level assigned Dynamic Time Warping (DTW) algorithm. The acquisition of online data is carried out by a digital pen equipped with pressures and inclination sensors. The time series obtained from pen during handwriting provide valuable insight to the unique characteristics of the writers. The obtained standard deviation values of time series are found person specific and are used as so called reference levels. In the proposed method reference levels are added to time series of query and sample dataset before dynamic time warping distance calculations. Experimental results show that the performance of accuracy in person authentication is improved and computational time is reduced.

[1]  Eamonn J. Keogh,et al.  Scaling up dynamic time warping for datamining applications , 2000, KDD '00.

[2]  Muzaffar Bashir,et al.  Reduced Dynamic Time Warping for Handwriting Recognition Based on Multidimensional Time Series of a Novel Pen Device , 2008 .

[3]  Yunhong Wang,et al.  On-line Signature Verification Using Segment-to-Segment Graph Matching , 2011, 2011 International Conference on Document Analysis and Recognition.

[4]  Hao Feng,et al.  Online signature verification using a new extreme points warping technique , 2003, Pattern Recognit. Lett..

[5]  O. Henniger,et al.  Effects of Time Normalization on the Accuracy of Dynamic Time Warping , 2007, 2007 First IEEE International Conference on Biometrics: Theory, Applications, and Systems.

[6]  Eamonn J. Keogh,et al.  Exact indexing of dynamic time warping , 2002, Knowledge and Information Systems.

[7]  Muzaffar Bashir,et al.  Person authentication with RDTW based on handwritten PIN and signature with a novel biometric smart pen device , 2009, 2009 IEEE Workshop on Computational Intelligence in Biometrics: Theory, Algorithms, and Applications.