DocumentCode
3636256
Title
Experimental comparison of segmentation algorithms on images of heat-emitting objects and methods for their accuracy improvement
Author
Tomasz Koszmider;Marcin Bąkała;Anna Fabijańska;Krzysztof Strzecha
Author_Institution
Department of Computer Engineering, Technical University of Lodz, 18/22 Stefanowskiego Str., 90-924, POLAND
fYear
2010
Firstpage
38
Lastpage
39
Abstract
In this paper problem of accurate segmentation of images presenting melted specimens of metal is considered. Firstly the theory of thermal phenomena influence on recorded images is explained. A review of most popular edge-based segmentation methods is provided. Results of applying drop shape analysis algorithm to segmented images are presented, analyzed and discussed.
Keywords
"Image segmentation","Probes","Shape","Algorithm design and analysis","Temperature","Surface tension","Image edge detection","Image analysis","Steel","Testing"
Publisher
ieee
Conference_Titel
Perspective Technologies and Methods in MEMS Design (MEMSTECH), 2010 Proceedings of VIth International Conference on
Print_ISBN
978-1-4244-7325-0
Type
conf
Filename
5499342
Link To Document