Artificial intelligence

Abstract: Article shows a comparative analysis of the efficiency of the recovery of low-contrast images, based on the use of self-organizing neural network methods of synthesis and linear prediction. Both methods allow to increase the sensitivity and spatial resolution of the visual analysis of low contrast luminance (one-dimensional) and multispectral images. The practical examples for comparing the effectiveness of different technologies (radiology, geographic information systems).

Keywords: low contrast image gradation, parametric model, nonlinear spectral analysis, neural network Kohonen vector of synaptic weights, the objective function, visual analysis.

References:

1. Gonsales R. Tsifrovaya obrabotka izobrazheniy. / R. Gonsales, Z. Vuds. – M.: Tehnosfera, 2006. –1070 s.
2. Yane B. Tsifrovaya obrabotka izobrazheniy / B. Yane – M.: Tehnosfera, 2007. – 583 s.
3. Ahmetshin O.M. Neyromerezheva segmentatsiya nizko kontrastnih zobrazhen’ geofizichnih poliv na osnovibagatoparametrovogo metodu nul-prostorovogo vidobrazhennya. / O.M. Ahmetshin, L.G. Ahmetshina. –GeoInformatika, KiIv, 2003, #2, S. 65-73.
4. Stepanenko A.A. Razlozhenie superpoziciy neizvestnyh impul'snyh signalov adaptivnym spektral'nymmetodom lineynogo predskazaniya / A.A. Stepanenko, A.M. Ahmetsin // Vestnik informacionnyh ikomp'uternyh tehnologiy, - M: Mashinostroenie. - 2006. №10. – S. 2-12.
5. Stepanenko A.A. Povishenie chuvstvitel'nosti ul'trazvukovoi diagnostiki na osnove metoda parametricheskogospektral'nogo analiza vtorogo poryadka / A.A. Stepanenko, A.M. Ahmetsin // Klinicheskaya informatika itelemedicina. – 2005. – Т.2. – №1. S. 98-100.
6. Slyunyaeva V.A. Povishenie chuvstvitel’nosti analiza slabo-kontrastnyh izobrazheniy na osnovesochetaniya metodov veyvlet preobrazovaniya I samoorganizuyuschegosya neyrosetevogo sinteza. /V.A. Slyunyaeva, A.M. Ahmetshyn. Materialy VI Mezhdunarodnoy nauchno-prakticheskoy konferenciymolodyh uchenyh I studentov “Informacionnye processy i tehnologiy «Informatika-2013»”: Sevastopol’22-26 kvitnya 2013 r. / SNTU – Sevastopol’: Veber, 2013. – S. 66-67.
7. Mala S. Veyvletyi v obrabotke signalov / S. Mala. – M., Mir, 2005. – 672 s.
8. Dobeshi I. Desyat’ lektsiy po veyvletam / I. Dobeshi. – Izhevsk, RHD, 2001. – 464 s.
9. Kohonen T. Samoorganizuyuschiesya kartyi / T. Kohonen. – M.: Binom, 2008. – 655 s.
10. Zlobin V.K., Eremeev V.V., Vasilev V.M. Stohasticheskaya model sputnikovyih izobrazheniy i eeispolzovanie dlya segmentatsii prirodnyih ob'ektov. / V.K. Zlobin, V.V. Eremeev, V.M. Vasilev //Avtometriya. - 2002. - # 2. - S. 41-50.
11. Solomatin I.I. Obzor metodov predvaritelnoy obrabotki tonovyih izobrazheniy dlya raspoznavaniyaiskusstvennyih ob'ektov. / I.I. Solomatin // Izv. vuzov. Priborostroenie. - 1996. - T. 39. - # 7. - S. 5-12.
12. Cheranovski K., Shver M. Kak otsenit kachestvo izobrazheniya? // Elektronnyiy zhurnal «Mostbezopasnosti», # 1, 2016. Rezhim dostupa: http://www.securitybridge.com/biblioteka/stati_po_bezopasnosti/kak_ocenit_kachestvo_izobrazheniya/