The influence of mismatching of input data on FIR filter coefficients generated by the neural network

• Autorzy: Pęksiński J. , Mikołajczak G.
• Języki publikacji: EN

Abstrakty

EN

In this article, the authors have presented the problem of inexact matching of input data in the learning process of a neural network generating a FIR filter in the form of a 5x5 mask. The obtained filter has the task of improving the quality of digital images acquired from acquisition devices, the construction and method of operation of which are based on a low-quality CCD matrix.

Słowa kluczowe

EN

neural network; FIR filter; mismatching of input data; learning process of a neural network

PL

sieć neuronowa; filtr FIR; niedopasowanie danych wejściowych; uczenie sieci neuronowej

• Wydawca: Wydawnictwo Politechniki Poznańskiej
• Czasopismo: Poznan University of Technology Academic Journals. Electrical Engineering
• Rocznik: 2011
• Tom: No. 66
• Strony: 129--136
• Opis fizyczny: Bibliogr. 7 poz., rys.

Twórcy

autor

Pęksiński J.

• West Pomeranian Technological University

autor

Mikołajczak G.

• West Pomeranian Technological University

Bibliografia

• [1] Osowski E.: Sieci neuronowe do przetwarzania informacji. Warszawa: OWPW 2000.
• [2] W W.K. Pratt „Digital Image Processing", PIKS Inside, Willey, 2001.
• [3] Pęksiński J. Kornatowski E. Mikołajczak G. Kowalski J.: Filtracja liniowa i nieliniowa obrazów dyskretnych. Szczecin Wydawnictwo Hogbefi 2005.
• [4] Gupta, P.K.; Kanhirodan, R." Design of a FIR Filter for Image Restoration using Principal Component Neural Networks" , Industrial Technology, 2006. ICIT 2006.IEEE International Conference on Volume , Issue , 15-17 Dec. 2006 Page(s):l177 -1182.
• [5] Z. Wang, Alan C. Bovik "Mean Squared Error: Love it or Leave it?", IEEE Signal Processing Magazine, 2009.
• [6] J.G Ackenhusen "Real-Time Signal Processing: Desing and Implementation of Signal Processing Systems", Upper Saddle River, PTR Prentice Hall 1999.
• [7] G. Thimm, E. Fiesler :Neural network initialization, in Form Neural to Artifical Neural Computation". Eds. J. Mira, Malaga 1995, pp. 533-542.