An Improved Geo-Textural Based Feature Extraction Vector For Offline Signature Verification

Main Article Content

Kennedy Gyimah
Justice Kwame Appati
Kwaku Darkwah
Kwabena Ansah

Abstract

In the field of pattern recognition, automatic handwritten signature verification is of the essence. The uniqueness of each person’s signature makes it a preferred choice of human biometrics. However, the unavoidable side-effect is that they can be misused to feign data authenticity. In this paper, we present an improved feature extraction vector for offline signature verification system by combining features of grey level occurrence matrix (GLCM) and properties of image regions. In evaluating the performance of the proposed scheme, the resultant feature vector is tested on a support vector machine (SVM) with varying kernel functions. However, to keep the parameters of the kernel functions optimized, the sequential minimal optimization (SMO) and the least square method was used. Results of the study explained that the radial basis function (RBF) coupled with SMO best support the improved featured vector proposed.

Keywords:
Signature Verification, Feature Extraction, Offline Signature Verification, Sequential Minimal Optimization, Kernel Function, Support Vector Machine

Article Details

How to Cite
Gyimah, K., Appati, J., Darkwah, K., & Ansah, K. (2019). An Improved Geo-Textural Based Feature Extraction Vector For Offline Signature Verification. Journal of Advances in Mathematics and Computer Science, 32(2), 1-14. https://doi.org/10.9734/jamcs/2019/v32i230141
Section
Original Research Article

Article Metrics


References

Diaz-Cabrera M, Morales A, Ferrer MA. Emerging issues for static handwritten signature
biometric. In In Advances in Digital Handwritten Signature Processing . A Human Artefact
for e-Society. 2014;111-122.

Hafemann LG, Sabourin R, Oliveira LS. Offline handwritten signature verification - literature
review. In In 7th Int. Conf. on Image Processing Theory, Tools and Applications (IPTA).
;1-5.

Impedovo D, Pirlo G, Plamondon R. Handwritten signature verification new advancements
and open issues. In In Int. Conf. on Frontiersin Handwriting Recognition.2012;367-372.

Neamah K, Mohamad D, Saba T, Rehman A. Discriminative features mining for offline
handwritten signature verification. 3D Research. 20145(3):1-6.

Jain AK, Ross A, Prabhakar S. An introduction to biometric recognition. IEEE Transactions
on Circuits and Systems for Video Technology. 2004;14(1):4-20.

Fotak T, Baca M, Koruga P. Handwritten signature identification using basic concepts of
graph theory. WSEAS Transactions on Signal Processing. 2011;7(4):117-129.

Khan S, Dhole A. A review on offline signature recognition and verification techniques.
International Journal of Advanced Research in Computer and Communication Engineering.
;3(6):6879-6882.

Argones Rua E, Maiorana E, Alba Castro JL, Campisi P. Biometric template protection
using universal background models: An application to online signature. IEEE Transactions
on Information Forensics and Security. 2012;7(1):269-282.

Ferrer MA, Diaz M, Carmona-Duarte C, Morales A. A behavioral handwriting model for
static and dynamic signature synthesis. IEEE Transactions on pattern analysis and machine
intelligence. 2017;39(6):1041-1053.

Liwicki M, Malik MI, Alewijnse L, van den Heuvel E, Found B. Handwritten signature
verification new advancements and open issues. In In 13th Int. Conf. on Frontiers in
Handwriting Recognition. IEEE. 2012;823-828.

Gomez-Barrero M, Galbally J, Fierrez J, Ortega-Garcia J. Hill-climbing attack based on the
uphill simplex algorithm and its application to signature verification. In In Proc. European
Workshop on Biometrics and Identity Management BioID (LNCS-6583). Springer. 2011;83-94.

Ortega-Garcia J, Fierrez-Aguilar J, Simon D, Gonzalez J, Faundez-Zanuy M, Espinosa V,
Satue A, Hernaez I, Igarza JJ, Vivaracho C. Mcyt baseline corpus: A bimodal biometric
database. IEEE Proceedings -Vision, Image and Signal Processing. 2003;150(6):395-401.

Shah DH, Shah TV. Signature recognition and verification: The most acceptable biometric
for security. proceedings of International journal of application and innovation in engineering
& management (IJAIEM); 2015.

Zois EN, Alewijnse L, Economou G. Offline signature verification and quality characterization
using poset-oriented grid features. Pattern Recognition. 2016;54:162-177.

Guerbai Y, Chibani Y, Hadjadji B. The effective use of the one-class svm classifier
for handwritten signature verification based on writer-independent parameters. Pattern
Recognition, 2015;48(1):103-113.

Paudel N, Querini M, Italiano GF. Online handwritten signature verification for low-end
devices. In International Conference on Information Systems Security and Privacy. 2016;25-
Springer.

Padmajadevi G, Aprameya K. A review of handwritten signature verification systems
and methodologies. In Electrical, Electronics, and Optimization Techniques (ICEEOT),
International Conference on. 2016;3896-3901. IEEE.

Barkoula K, Economou G, Fotopoulos S. Online signature verification based on signatures
turning angle representation using longest common subsequence matching. Int. Journal on
Document Analysis and Recognition, 2013;16(3):261-272.

Houmani N, Garcia-Salicetti S, Dorizzi B. On assessing the robustness of pen coordinates,
pen pressure and pen inclination to timevariability with personal entropy. In In IEEE 3rd Int.
Conf. on Biometrics: Theory, Applications, and Systems. 2009;1-6.

Pal S, Pal U, Blumenstein M. Off-line verification technique for hindi signatures. IET
biometrics. 2013;2(4):182-190.

Wang D, Zhang Y, Yao C, Wu J, Jiao H, Liu M. Toward force-based signature verification:
A pen-type sensor and preliminary validation. IEEE Transactions on Instrumentation and
Measurement. 2010;59(4):752-762.

Pratikakis I, Gatos B, Ntirogiannis K. Icfhr 2014 competition on handwritten document image
binarization. In H-DIBCO. 2014;809-813.

Vo QN, Kim SH, Yang HJ, Lee G. Binarization of degraded document images based on
hierarchical deep supervised network. Pattern Recognition. 2018;74:568-586.
Karthikaa M, James A. A novel approach for document image binarization using bit-plane
slicing. Procedia Technology. 2015;19:758-765.

Arvind KR, Kumar J, Ramakrishnan AG. Line removal and restoration of handwritten strokes.
In Proc. of IEEE International Conference on Computational Intelligence and Multimedia
Applications. 2007;208-214.

Diaz M, Ferrer MA, Eskander GS, Sabourin R. Generation of duplicated off-line signature
images for verification systems. IEEE Transactions on pattern analysis and machine
intelligence. 2017;39(5):951-964.

Zhu G, Zheng Y, Doermann D, Jaeger S. Signature detection and matching fordocument image
retrieval. IEEE Transactions on Software Engineering. 2015;31(11):951-964.


Abu-Ain W, Abdullah SNHS, Bataineh B, Abu-Ain T, Omar K. Skeletonization algorithm for
binary images. Procedia Technology. 2013;39(5):704-709.

Zois EN, Theodorakopoulos I, Economou G. Offline signature verification and quality
characterization using poset-oriented grid features. Pattern Recogn.. 2016;54:162-177.

Appati JK, Obed Fosu G, Gogovi GK. Face feature extraction for recognition using radon
transform. American Journal of Engineering Research. 2014;3(3):219-224.

Hiryanto L, Yohannis AR, Handhayani T. Hand signature and handwriting recognition as
identification of the writer using gray level co-occurrence matrix and bootstrap. In 2017
Intelligent Systems Conference (IntelliSys). 2017;1103-1110.

Hanusiak RK, Oliveira LS, Justino E, Sabourin R. Writer verification using texture-based
features. International Journal on Document Analysis and Recognition. 2015;15(3):213-226.

Haralick RM, Shanmugam K, Dinstein I. Texture features for images classification. IEEE
Transaction on Systems, Man, and Cybernetics. SMC. 1973;3(6):610-621.

Ohanian PP, Dubes RC. Performance evaluation for four classes of textural features. Pattern
Recognition. 1992;25(8):819-833.

Ojala T, Pietikinen M, Menp T. Multiresolution gray-scale and rotation invariant texture
classification with local binary patterns. IEEE Transactions on Pattern Analysis and Machine
Intelligence. 2002;24(7):971-987.

Tamura H, Mori S, Yamawaki T. Textural features corre- sponding to visual perception. IEEE
Transaction on System, Man and Cybernetics. 1978;8(6):460-473.

Cortes C, Vapnik V. Support-vector networks. Machine Learning. 1995;20(3):273-297.

Chang CC, Lin CJ. Libsvm: a library for support vector machines. ACM Transactions on
Intelligent Systems and Technology. 2011;2(3):1-27.

Diaz-Cabrera M, Gomez-Barrero M, Morales A, Ferrer MA, Galbally J. Generation of enhanced
synthetic off-line signatures basedon real on-line data. In 14th Int. Conf. on Frontiers in
Handwriting Recognition (ICFHR). 2014;482-487.

Diaz-Cabrera M, Ferrer MA, Morales A. Cognitive inspired model to generate duplicated static
signature images. In Int. Conf. onFrontiers in Handwriting Recognition (ICFHR). 2014;61-66.

Gruber C, Gruber T, Krinninger S, Sick B. Online signature verification with support vector
machines based on lcss kernel functions. IEEE Trans. on Systems, Man, and Cybernetics.
;40(4):1088-1100.

Appati JK, Gogovi GK, Obed Fosu G. On the selection of appropriate kernel function for
svm in face recognition. International Journal of Advanced Research in Computer Science and
Software Engineering. 2014;4(3):6-9.

Zhang S, Li F. Off-line handwritten chinese signature verification based on support vector
machine multiple classifiers. In Advancesin Electric and Electronics, Springer. 2012;563-568.

Pal S, Pal U, Blumenstein M. Hindi and english off-line signature identification and verification.
In Proceedings of Int. Conf. on Advancesin Computing. Springer. 2013;905-910.

Guerbai Y, Chibani Y, Hadjadji B. The effective use of the one-class svm classifier
for handwritten signature verification based onwriter-independent parameters. Pattern
Recognition. 2015;48(1):103-113.

Ferrer MA, Diaz-Cabrera M, Morales A. Synthetic off-line signature image generation. In Int.
Conf. on Biometrics, IEEE. 2013;1-7.

Osuna E, Freund R, Girosi F. An improved training algorithm for support vector machines.
In Neural Networks for Signal Processing, IEEE. 1997;276-285.

Suykens JAK, Vandewalle J. Least squares support vector machine classifiers. Neural
Processing Letters. 1999;9(3):293-300.

Amoako-Yirenkyi P, Frempong NK, Appati JK, Hafron-Acquah JB, Dontwi IK. Threshold
analysis of wavelet based fingerprint feature extraction methods on multiple impression dataset.
British Journal of Mathematics & Computer Science. 2015;5(3):383-396.

Vargas J, Ferrer M, Travieso C, Alonso JB. Off-line signature verification based on grey level
information using texture features. Pattern Recognition. 2011;44(2):375-385.

Shekar B, Bharathi R, Kittler J, Vizilter YV, Mestestskiy L. Grid structured morphological
pattern spectrum for off-line signature verification. In 2015 International Conference on
Biometrics (ICB). 2015;430-435. IEEE.

Hafemann LG, Sabourin R, Oliveira LS. Writer-independent feature learning for offline
signature verification using deep convolutional neural networks. In Neural Networks (IJCNN),
International Joint Conference on. 2016;2576-2583. IEEE.