Optimization of the use of traditional segmentation algorithms for defect detection tasks in industry
Optimalizace využití tradičních segmentačních algoritmů pro úlohy detekce defektů v průmyslu
Authors
Supervisors
Reviewers
Editors
Other contributors
Journal Title
Journal ISSN
Volume Title
Publisher
České vysoké učení technické v Praze
Czech Technical University in Prague
Czech Technical University in Prague
Date
Abstract
Práce porovnává algoritmy určené k segmentaci objektu v obraze. Porovnány jsou tři algoritmy řadící se do kategorie superpixels (felzenszwalb, SLIC a quickshift), dva zástupci active contour models (snakes a level sets), random walker, region adjacency graphs a Otsu prahování. K tomuto účelu jsou zmapovány defekty objevující se v průmyslu. Nad defekty je vytvořena obecnější kategorizace. Následně jsou z každé kategorie vybrány dvě vady. Na první vadě je nalezena vhodná kombinace parametrů. U hledání jsou zohledněny efekty různého předzpracování a reprezentace snímku pomocí odlišných barevných prostorů. S nalezenými parametry je provedena segmentace druhé vady. Tak je otestována schopnost generalizace a vhodnost použití algoritmu pro vady dané kategorie. Úspěšnost segmentace je měřena metrikou IOU. Úspěšnější algoritmy dosáhly průměrného IOU měřeného přes všechny snímky jedné vady 90 %. U testu generalizace bylo v některých případech dosaženo průměrného IOU 53 %.
The paper compares algorithms designed for image segmentation. Three algorithms belonging to the category of superpixels (felzenszwalb, SLIC and quickshift), two representatives of active contour models (snakes and level sets), random walker, region adjacency graphs and Otsu thresholding are compared. For this purpose, defects appearing in the industry are described. A more general categorization splitting defects into groups is made. Subsequently, two defects are selected from each category. A suitable combination of algorithm parameters is found on the first defect. Different preprocessing and color representation of the image are accounted for when the search is carried out. With the found parameters, a segmentation of the second defect is performed. Thus, the generalization capability and the suitability of the algorithm for the defects of the given category are tested. The success of the segmentation is measured by the IOU metric. The more successful algorithms achieved an average IOU measured over all images of a single defect of 90 %. In generalization test an average IOU of 53 % was achieved in some cases.
The paper compares algorithms designed for image segmentation. Three algorithms belonging to the category of superpixels (felzenszwalb, SLIC and quickshift), two representatives of active contour models (snakes and level sets), random walker, region adjacency graphs and Otsu thresholding are compared. For this purpose, defects appearing in the industry are described. A more general categorization splitting defects into groups is made. Subsequently, two defects are selected from each category. A suitable combination of algorithm parameters is found on the first defect. Different preprocessing and color representation of the image are accounted for when the search is carried out. With the found parameters, a segmentation of the second defect is performed. Thus, the generalization capability and the suitability of the algorithm for the defects of the given category are tested. The success of the segmentation is measured by the IOU metric. The more successful algorithms achieved an average IOU measured over all images of a single defect of 90 %. In generalization test an average IOU of 53 % was achieved in some cases.
Description
Keywords
porovnání algoritmů, segmentace objektů, detekce defektů, zpracování obrazu, strojové vidění, active contour, random walker, superpixels, region adjacency grafy, prahování Otsu, algorithm comparison, object segmentation, defect detection, image processing, computer vision, active contour, random walker, superpixels, region adjacency graphs, Otsu thresholding