DocumentCode :
3166585
Title :
Graphs structure analysis method for boundary recognition in images with adjoining objects
Author :
Kosinski, C.
Author_Institution :
Warsaw Univ. of Technol., Poland
fYear :
1995
fDate :
4-6 Jul 1995
Firstpage :
737
Lastpage :
741
Abstract :
An undirected graph approach to enhance the quality of the process of boundary recognition is presented. The co-ordinates of the vertices and edges of the graph are fixed and connected with specific pixels. This allows to combine advantages of both graph theory and 2D spatial image analysis. The algorithm presented is much more efficient than conventional techniques when used for images with high noise and severe disturbances
Keywords :
edge detection; graph theory; image enhancement; interference (signal); 2D spatial image analysis; adjoining objects; boundary recognition; co-ordinates; edges; graph theory; graphs structure analysis method; noise; severe disturbances; undirected graph approach; vertices;
fLanguage :
English
Publisher :
iet
Conference_Titel :
Image Processing and its Applications, 1995., Fifth International Conference on
Conference_Location :
Edinburgh
Print_ISBN :
0-85296-642-3
Type :
conf
DOI :
10.1049/cp:19950757
Filename :
465624
Link To Document :
بازگشت