'Multistep algorithms of image segmentation: principles of development and process visualization' Software systems and computational methods nbpublish.com
Eng Cn Translate this page:
Please select your language to translate the article


You can just close the window to don't translate
Library
Your profile

Kuzmin S.A. Multistep algorithms of image segmentation: principles of development and process visualization

Published in journal "Software systems and computational methods", 2014-1 in rubric "Computer graphics, image processing and pattern recognition", pages 93-108.

Resume: The article reviews a problem of a video stream frames segmentation in a bottom-upwards approach, which cant be solved in a single processing step due to errors in binarization. For achieving the desired accuracy some additional processing units are needed, the working of each one end with a shift of working receiver operating characteristic (ROC). Intermediate positions of the displaced characteristic is saved in the operating points set up after each shift. The set of operating point makes a path to the area of required accuracy. This its only needed to match the sequence of processing units to get the required accuracy. The author developed a classification of approaches to segmentation in the bottom-upwards analysis that allows to determine the most effective processing units. A system of video analysis meeting the most recommendations was developed. Each block of segmentation is represented by a family of algorithm allowing to determine object coordinates with required accuracy, including subpixel accuracy. Fot the described system of video analysis the article presents its path and criteria for selecting operating points during the setup. The discussed classification approaches to segmentation along with criteria for selecting operating points and visualization method can be used in developing other systems of video analysis.

Keywords: wavelet transform, segmentation, image pyramid, ROC- characteristics, criterion, visualization, bottom-upwards, sub-pixel accuracy, classification, video data

DOI: 10.7256/2305-6061.2014.1.11505

This article can be downloaded freely in PDF format for reading. Download article

Bibliography:
P. J. Burt and E. H. Adelson, The Laplacian pyramid as a compact image code. IEEE Transactions on Communications, vol. 31, no. 4, pp. 532-540, April 1983.
N. Nguyen and P. Milanfar. A wavelet-based interpolation-restoration method for superresolution (wavelet superresolution). IEEE Transactions on Circuits, Systems, and Signal Processing, Vol. 19, No. 4, 2000, pp. 321-338.
Chochia P.A. Piramidal'nyy algoritm segmentatsii izobrazheniy // Informatsionnye protsessy, Tom 10, No 1, 2010. S. 2335.
Motyko A.A. Obrabotka i analiz videodannykh v sistemakh monitoringa dvizhushchikhsya ob'ektov: avtoref. dis. na soisk. uchenoy step. kand. tekhn. nauk: 05.13.01: zashchishchena 22.05.2012 / A. A. Motyko. SPb., 2012. 20 s.
Kharatishvili N.G., Chkheidze I.M. Morfologicheskie postroeniya v kodirovanii izobrazheniy. Tbilisi: Gruzinskiy tekhnicheskiy universitet, 2009. 144 s.
Malashkevich I.A., Malashkevich V.B. Effektivnyy algoritm detsimatsii dannykh // NB: Kibernetika i programmirovanie.-2013.-5.-C. 1-6. DOI: 10.7256/2306-4196.2013.5.9697. URL: http://www.e-notabene.ru/kp/article_9697.html
Kuz'min S. A. Issledovanie kombinatsii detektora impul'snogo shuma v binarnykh izobrazheniyakh i protsentil'nykh fil'trov// Estestvennye i matematicheskie nauki v sovremennom mire: materialy IX mezhdunarodnoy zaochnoy nauchno-prakticheskoy konferentsii. (19 avgusta 2013 g.) Novosibirsk: Izd. SibAK, 2013. C. 34-44.
Kuz'min S.A. Issledovanie tochnosti segmentatsii podvizhnykh ob'ektov s ispol'zovaniem veyvletov semeystva Dobeshi// Nauchnaya sessiya GUAP: Sb. dokl.: V 3 ch. Ch.II. Tekhnicheskie nauki /SPbGUAP. SPb., 2008. S. 32-35.
Kuz'min S. A. Segmentatsiya posledovatel'nostey izobrazheniy s reguliruemoy tochnost'yu i vizualizatsiya effektivnosti// Tekhnicheskie nauki ot teorii k praktike. 8 (21): sbornik statey po materialam XXV mezhdunarodnoy nauchno-prakticheskoy konferentsii. Novosibirsk: Izd. SibAK, 2013. C. 44-54.
Kuz'min S.A. Obnaruzhenie vizual'nykh ob'ektov s ispol'zovaniem veyvlet-preobrazovaniya i otsenivaniya fona//Sistemy upravleniya i informatsionnye tekhnologii, 2.1(28), 2007. S. 158-162.
Kuz'min S.A. Obnaruzhenie dvizhushchikhsya vizual'nykh ob'ektov na osnove vydeleniya oblastey i konturov, ne prinadlezhashchikh fonu// Molodye uchenye-promyshlennosti Severo-Zapadnogo regiona: Materialy konferentsiy politekhnicheskogo simpoziuma. Dekabr' 2006 goda. SPb.: Izd-vo Politekhn. un-ta, 2006. S. 56.
Boguslavskiy, A.A. Metody programmirovaniya sistem tekhnicheskogo zreniya real'nogo vremeni: avtoref. dis. na soisk. uchenoy step. doktora fiziko-matem. nauk: 05.13.11: zashchishchena 14.11.2006/ A.A. Boguslavskiy; Institut prikladnoy matematiki im. M.V. Keldysha RAN. Moskva, 2006. 36 c.
Aleksandrov V.V., Gorskiy N.D. Predstavlenie i obrabotka izobrazheniy. Rekursivnyy podkhod. L.: Nauka, 1985. 192 s.
Amirkhanov S.G., Obukhova N.A. Metod avtomaticheskoy segmentatsii i soprovozhdeniya ob'ektov na osnove korrelyatsionnogo sovmeshcheniya i polya vektorov dvizheniya// Materialy 6-oy MK Televidenie: peredacha i obrabotka izobrazheniy. SPb, 2008. S. 48-51.
M.A. Shcherbakov, W.Y. Schegolev. A Wavelet-based Technique for Image Refinement. EUSIPCO-2000, Tampere, pp.1737-1739.
Zhen Xie, A Wavelet Based Algorithm for Image Super-Resolution/ Master of Science thesis. USA, Atlanta GA: Emory University, December 2007. 63 p.

Correct link to this article:
just copy this link to clipboard