Combined static and dynamic features types for online signature verification
Date of Publication
2007
Document Type
Bachelor's Thesis
Degree Name
Bachelor of Science in Computer Science
College
College of Computer Studies
Department/Unit
Computer Science
Thesis Adviser
Jocelynn W. Cu
Defense Panel Member
Nelson Marcos
Jose Ronello T. Bartolome
Abstract/Summary
A new online signature verification using static and dynamic features is presented. Static features are characteristics of signatures that pertain to the shaper of the signature. On the other hand dynamic features are concerned with characteristics related to time. The combination of both feature types is used to address multiple types of forgery namely the random, simple and skilled.
The four (4) major steps for signature are preprocessing, feature extraction, template generation and verification. Size normalization, Gaussian filter and baseline correction are used for preprocessing the signature. Features used in the system include velocity of X, velocity of Y,X,Y, [X.Y]., sin, cosine an curvature. Dynamic Time Warping (DTW) is used for both template generation and verification due to the variances in tome of the features. The experimental results showed a decrease in FAR and an increase in FRR when combining both feature types. Overall the result yielded a 3.8% FAR and a 24.0% FRR for all types if forgeries."
Abstract Format
html
Language
English
Format
Accession Number
TU14643
Shelf Location
Archives, The Learning Commons, 12F, Henry Sy Sr. Hall
Recommended Citation
Gan, N. H., Lao, A. S., Marasigan, R. N., & Trinidad, M. C. (2007). Combined static and dynamic features types for online signature verification. Retrieved from https://animorepository.dlsu.edu.ph/etd_bachelors/14432