USING CHARACTER RECOGNITION METHODS TO DETERMINE THE AUTHENTICITY OF A PERSONAL SIGNATURE

Authors

  • Shchur Vadym National Technical University of Ukraine "Igor Sikorsky Kyiv Polytechnic Institute", Ukraine
  • Steshyn Viktor National Technical University of Ukraine "Igor Sikorsky Kyiv Polytechnic Institute", Ukraine

Abstract

The paper deals with the analysis and improvement of existing methods of character recognition to determine the authenticity of a personal signature. To do this, using neural networks, learning opportunities and increasing the accuracy of which, can effectively solve the problems of definition in terms of diversity and inaccuracy of handwritten signatures. The recognition system trains on the basis of repeated input of personal signatures and establishes the corresponding weights of the neural network.

 

Key words: character recognition, convolutional neural networks, multilayer perceptron, network learning.

Fig.: 4. Bibl.: 5.

Published

2023-11-08

Issue

2018

Section

Machine learning, Big Data