Algorithmic and software means of handwritten symbols recognition.

2017;
: pp. 98 - 106
1
Lviv Polytechnic National University, Computer Engineering Department
2
Lviv Polytechnic National University, Computer Engineering Department

In this article is considered the algorithm of logistic regression and construction of the neural network for the recognition of handwritten symbols in the image. Examples of implementation of two approaches for solving the problem of numerical recognition are given. The efficiency of using a neural network, as the provision of the most reliable recognition results, is explored.

  1. Expression of images recognition [Electronic resource], wiki, Access mode: https://uk.wikipedia.org/wiki/Requirements recognition.
  2. Lukin V. E. Analysis of the use of technology of artificial neural networks as a new approach to signal processing, V. Lukin, Telecommunication and information technologies, 2014 – P. 81–82.
  3. Artificial_neuronal_network [Electronic resource], wiki, Access mode: https://uk.wikipedia.org/wiki/New_neuronal_network.
  4. What is machine learning [Electronic resource], Coursera, Access mode: https://www.coursera.org/learn/machinelearning/supplement/aAgxl/what-is-...
  5. Machine learning [Electronic resource], Coursera, Access mode: https://www.coursera.org/learn/machine-learning/home/week/3.
  6. Backpropagation algorithm [Electronic resource], Coursera, Access mode: https://www.coursera.org/learn/machine-learning/supplement/pjdBA/backpro....
  7. How the backpropagation algorithm works [Electronic resource], Neuralnetworksanddeeplearning, Access mode: http://neuralnetworksanddeeplearning.com/chap2.html.
Paramud Y. Algorithmic and software means of handwritten symbols recognition / Y. Paramud, V. Yarkun // Visnyk Natsionalnoho universytetu "Lvivska politekhnika". Serie: Kompiuterni systemy ta merezhi. — Lviv : Vydavnytstvo Lvivskoi politekhniky, 2017. — No 881. — P. 98–106.