SIGNATURE RECOGNITION ALGORITHMS. BEZIER ALGORITHM

This article focuses on improving the human and machine interface, which should ensure efficient processing of data and knowledge in simple, fast and accessible ways. One of the ways to organize it is the introduction of the manuscript (entering text, drawings, drawings, etc.). Handwritten signatures can be considered as handwritten words, but they are more suitable for drawings, because the signer tries to make his signature unique, using not only his first and last names, but also additional graphic elements. Creating a signature is quite simple, although it is impossible to reproduce the recording speed.

The signature has long been used to certify the authenticity of documents and verify (authenticate) an individual. In principle, the signature examination is used during the forensic examination. Signature recognition can be carried out by sequential verification of the signature to each known person. The signature recognition methodology includes a verification methodology and processing of verification results. One of the modern areas of interface improvement is the development and research of software for signature recognition and visualization.

The advent of modern computer input tools has led to the emergence of a new type of online signature describing the signature creation process, not the result. Moreover, not only the coordinates of points on the line, but also a sequence of vectors of parameter values for each of the values of pressure, direction and speed of movement, the angle of adaptation of the pen and the signature time.

1. Tolosana, R. Biometric Signature Verification Using Recurrent Neural Networks / R. Tolosana, R. Vera Rodriguez, J. Fierrez, J. Ortega-Garcia // Proceedings of the International Conference on Document Analysis and Recognition, 2018. – Vol. 1. – pp. 652-657.

2. Iranmanesh, V. Online Handwritten Signature Verification Using Neural Network Classifier Based on Principal Component Analysis / V. Iranmanesh, S.M.S. Ahmad, W.A.W. Adnan, S. Yussof, O.A. Arigbabu, F.L. Malallah // The Scientific World Journal, 2014. – Vol. 2014. – pp. 1-8.

3. Cpalka, K. New method for the on-line signature verification based on horizontal partitioning / K. Cpalka, M. Zalasinski, L. Rutkowski // Pattern Recognition, 2014. – Vol. 47. – pp. 2652-2661.

4. Calik, N.Signature recognition application based on deep learning / N. Calik, O.C. Kurban, A.R. Yilmaz // 25th Signal Processing and Communications Applications Conference, 2017.

5. Anikin, I.V. Handwritten signature recognition method based on fuzzy logic / I.V. Anikin, E.S. Anisimova // 2016 Dynamics of Systems, Mechanisms and Machines, Dynamics 2016.

6.