**Streszczenie**

This article describes the architecture of the Hamming-Lippmann neural network and the math of the modified learning-recognition algorithm and presents some practical aspects for using it for solving an image recognition task. We have created software using C# programming language, that utilized this network as an additional error-correcting procedure, and have solved the task of recognition highly corrupted QR codes (with a connection to the database). Experimental results, of finding the optimal parameters for this algorithm, are presented. This neural network doesn't require time-consuming computational procedures and large amounts of memory, even for high-resolution and big size images.

**Słowa kluczowe:**

*neuron, Hamming-Lippmann neural network, learning-recognition algorithm, image processing, sliding window mode, computational complexity, image recognition, error-correction, QR codes.*

**Abstract**

W tym artykule opisano architekturę sieci neuronowej Hamminga-Lippmanna oraz matematykę zmodyfikowanego algorytmu rozpoznawania uczenia się, a także przedstawiono kilka praktycznych aspektów korzystania z niej w celu rozwiązania zadania rozpoznawania obrazu. Stworzyliśmy oprogramowanie wykorzystujące język programowania C #, który wykorzystał tę sieć jako dodatkową procedurę korekty błędów i rozwiązaliśmy zadanie rozpoznawania wysoce uszkodzonych kodów QR (w połączeniu z bazą danych). Przedstawiono wyniki eksperymentalne poszukiwania optymalnych parametrów dla tego algorytmu. Opisywana neuronowa nie wymaga czasochłonnych procedur obliczeniowych i dużej ilości pamięci, nawet w przypadku obrazów o wysokiej rozdzielczości i dużych rozmiarach.

**Keywords:**

*neuron, sieć neuronowa Hamminga-Lippmanna, algorytm rozpoznawania, przetwarzanie obrazu, przesuwne okno, złożoność obliczeniowa, rozpoznawanie obrazu, korekcja błędów, kody QR, optymalne parametry.*

The beginning of the neural networks history is connected with the "connectionist models" or "parallel distributed processing", that are considered in the publication in 1943 of McCulloch and Pitts. These scientists proposed general approaches and specific mathematical models of the biological neural networks and their components - neurons, that became fundamental in the artificial neural networks theory. These neurons were presented as models of the biological neurons and as conceptual components for circuits, that performed computational tasks. They used threshold elements with two stable states, which are called “McCallock-Pitts neurons" [1]. The task of developing models and systems, which are based on the threshold elements was so unusual and complex, that only in 1956 was appeared the first capable artificial neural network - Rosenblatt perceptron. Its demonstrated the possibility of creating technical patterns, based on the models of the human brain, for image recognition. However, further researches of perceptrons showed, that their usage in the recognition systems is associated with many difficulties. In 1969 Minsky and Papert published their book, in which they described the deficiencies of the perceptron model and showed their fundamental nature. The negative prognosis of the authoritative scientists caused a decline in the interest in neural networks, which lasted more than ten years, but in the 80's after some important theoretical results, the neural networks began to rebound. The renewed interest is reflected in many researches, the amounts of funding, the number of conferences and journals associated with neural networks [2,3]. At the same time, neurocomputing begins to develop, which allows solving problems from different areas of knowledge using neural networks, which are modelled on ordinary computers [4]. The machine interpretation of the neural network came into the world of Computer [...]

## Prenumerata

**Bibliografia**

[1] McCulloch W., Pitts W., A Logical Calculus of Ideas Immanent
in Nervous Activity, Bulletin of Mathematical Biophysics, 5
(1943), 115-133

[2] Smagt van der P., Krose, B., An Introduction to Neural
Networks, Netherlands, University of Amsterdam, Faculty of
Mathematics and Computer Science (1996), 15-19.

[3] Haykin S., Neural Networks: A Comprehensive Foundation,
New Jersey, Prentice Hall, (1994), 89-97

[4] Norvig P., Russel S., Artificial Intelligence, New Jersey,
Prentice Hall, (2009), 863-902

[5] Król K., Inverse problem solution using neural network,
Informatyka, Automatyka, Pomiary w Gospodarce i Ochronie
Środowiska - IAPGOS, 2(2012), no. 1., 9-11

[6] Caudill, M., Neural Networks Primer, Part I, AI Expert, 2(1987),
46-52

[7] Goyal S., Goyal G.K., Advanced Computing Research on
Cascade Single and Double Hidden Layers for Detecting Shelf
Life of Kalakand: An Artificial Neural Network Approach,
International Journal of Computer Science and Emerging
Technologies, 2(2011), 292-295

[8] Mason J., Ellacott S.W., Mathematics of Neural Networks,
Springer, (1997), 3-15

[9] Wójcik W., Kotyra A., Golec T. et al., Vision based monitoring
of coal flames, Przegląd Elektrotechniczny, 87 (2008), n.3, 241-
243

[10] Lippmann, R., An Introduction to Computing with Neural Nets,
IEEE ASSP Magazine, 4(1987), 4-22

[11] Morelos-Zaragoza R., The Art of Error Correction Coding,
John Wiley&Sons, (2006), 27-39

[12] Lippmann R., Gold B., Malp M.L., A Comparison of Hamming
and Hopfield Neural Nets for Pattern Classification, Cambridge,
Massachusetts Institute of Technology, Technical Report 769,
41 p. (1987)

[13] Koutroumbas K., Kalouptsidis N., Generalized Hamming
Networks and Applications, Neural Networks, 18(2005), 896-
913

[14] Gonzalez, R.C., Woods, R.E., Digital Image Processing,
Prentice-Hall, (2008), 206-253

[15] Fausett L., Fundamentals of Neural Networks: Architectures,
Algorithms, and Applications, Prentice-Hall, (1994), 158-169

[16] Callan R., The Essence of Neural Networks, Prentice Hall,
(1999), 108-116

[17] Luger G., Artificial Intelligence: Structures and Strategies for
Complex Problem Solving, Addison Wesley, 29-38 (2005).

[18] Rojas R., Neural Networks, Springer Science & Business
Media, (1996), 23-27

[19] Stolarczuk P.; Yatsuk V.; Majewski J., Małaczywski P.,
Michalewa M. Usage of capacitive sensors for fast checking of
parameters of multicomponent solutions. Przegląd
Elektrotechniczny, 86 (2010), No. 10, 92-95.

[20] Toliupa S., Kravchenko Y., Trush A., Organization of
implementation of ubiquitous sensor networks, Informatyka,
Automatyka, Pomiary w Gospodarce i Ochronie Środowiska -
IAPGOS, 8(2018), no. 1., 36-39

[21] Heaton J., Introduction to Neural Networks for C#, Heaton
Research, (2008), 39-137

[22] Wójcik W., Smolarz A., Information Technology in Medical
Diagnostics, Taylor &Francis Group CRC Press Reference,
(2017), 210

[23] Vassilenko V., Valtchev S., Teixeira J.P., Pavlov S., Energy
harvesting: an interesting topic for education programs in
engineering specialities, Internet, Education, Science, (2016),
149-156

[24] Krak Yu.V., Dynamics of manipulation robots: Numericalanalytical
method of formation and investigation of
computational complexity, Journal of Automation and
Information Sciences, 31(1999), no. 1-3, 121-128