Powiadomienia systemowe
- Sesja wygasła!
Identyfikatory
Warianty tytułu
Konferencja
Conference on Computer Graphics and Image Processing, GKPO' 2000 (6 ; 15-19.05.2000 ; Polesie, Poland)
Języki publikacji
Abstrakty
This paper describes an approach to the problem of fault detection. Fault detection is considered hare as a segmentation task. One need to segment the initial image in order ti find areas of a particular kind - failts. The approach presented combines the mathematical morphology and clustering. The morphological treatment is based on morphological filtering by reconstruction but it includes also some other tools like top-hat transformation and contrast improvement. Clustering is performed by the k-means algorith. Three methods of fault detection are presented here. Each of them is destined to the segmentation of the images of different kind.
Czasopismo
Rocznik
Tom
Strony
215--220
Opis fizyczny
Bibliogr. 10 poz.
Twórcy
autor
- Institute of Control and Industrial Electronics, Warsaw University of Technology ul. Koszykowa 75, 00-662 Warszawa, iwanowski@isep.pw.edu.pl
Bibliografia
Typ dokumentu
Bibliografia
Identyfikator YADDA
bwmeta1.element.baztech-article-BWA1-0001-0815