Radiotekhnika
Publishing house Radiotekhnika

"Publishing house Radiotekhnika":
scientific and technical literature.
Books and journals of publishing houses: IPRZHR, RS-PRESS, SCIENCE-PRESS


Тел.: +7 (495) 625-9241

 

Spatial adaption method of gradient masks to segment countours of objects on the noised images

Keywords:

M.A. Pantyukhin – Post-graduate Student, MESC «Zhukovsky–Gagarin Air Force Academy» (Voronezh). E-mail: ol-max@mail.ru E.A. Samoylin – Dr. Sc. (Eng.), Associate Professor, Professor, MESC «Zhukovsky–Gagarin Air Force Academy» (Voronezh). E-mail: es977@mail.ru R.V. Belyaev – Head of Research Centre, MESC «Zhukovsky–Gagarin Air Force Academy» (Voronezh) A.V. Nagalin – Ph. D. (Eng.), Associate Professor, Deputy Head, MESC «Zhukovsky–Gagarin Air Force Academy» (Voronezh)


Currently, the vast majority of recognition operators used in various optoelectronic systems focused on contour representation of an object, which can be obtained using first and second derivatives. Meanwhile, pulse noises arising due to organized optoelectronic countermeasures reduce the efficiency due to errors first and second kind when such algorithms detect the contour elements. This leads to decrease signal to noise ration and finally decreases the probability of detection and identification. An adaptive algorithms based on gradient masks can’t work correctly in considerable intensity cases. That’s why the goal of this paper is to enhance the accuracy of gradient segmentation contours objects features on digital images recorded in cases of optoelectronic countermeasures. The idea of the proposed method is to adapt form and values of gradient masks coefficients depending on damaged elements in mask standard size. Binary matrix show allocation impulse noise is formed previously. Presented results of numerical studies show that the proposed method has fewer total errors of the first and second order compared to the well-known algorithms even adaptive procedures. However it has more complex computing.
References:

 

  1. Doncov A.A., Kozirackijj JU.L. Algoritm lokalizacii malorazmernykh obektov na izobrazhenii s ispolzovaniem vejjvlet-preobrazovanijj // Avtometrija. 2013. T. 49. № 2. S. 42−48.
  2. Alpatov B.A., Babajan P.V., Smirnov S.A. Avtomaticheskoe slezhenie za obektami pri otsutstvii apriornykh svedenijj o fonocelevojj obstanovke // Cifrovaja obrabotka signalov. 2009. № 3. S. 52−56.
  3. Muravev V.S., Muravev S.I. Adaptivnyjj algoritm vydelenija i obnaruzhenija vozdushnykh obektov na izobrazhenijakh // Informacionno-upravljajushhie sistemy. 2011. № 5. S. 8−14.
  4. Sirota A.A., Solomatin A.I. Poisk mnozhestva obektov na osnove invariantnykh preobrazovanijj ehtalonnykh fragmentov izobrazhenija // Informacionno-izmeritelnye i upravljajushhie sistemy. 2010. № 6. S. 8−15.
  5. Pantjukhin M.A., Samojjlin E.A. Algoritm adaptivnogo vydelenija konturov obektov na cifrovykh izobrazhenijakh, registriruemykh v uslovijakh destruktivnykh lazernykh pomekh // Radiotekhnika. 2015. № 12. S. 60−65.
  6. Samojjlin E.A. Metod adaptacii masok v zadachakh gradientnogo vydelenija konturov izobrazhenijj na fone impulsnykh pomekh // Izvestija RAN. Teorija i sistemy upravlenija. 2010. № 2. S. 118−129.
  7. Samojjlin E.A. Sintez statisticheski optimalnykh obnaruzhitelejj impulsnykh pomekh pri filtracii izobrazhenijj // Radiotekhnika. 2009. № 9. S. 25−31.

 

© Издательство «РАДИОТЕХНИКА», 2004-2017            Тел.: (495) 625-9241                   Designed by [SWAP]Studio