Deakin home > Deakin University Library > Deakin Research Online > Object extraction using genetic algorithms and morphological processing

Object extraction using genetic algorithms and morphological processing

Zheng, Hong, Pan, Li and Nahavandi, Saeid 2002, Object extraction using genetic algorithms and morphological processing, in SPIE 2002 : Color science and imaging technologies : 16-17 October, 2002, Shanghai, China, SPIE, Washington, D.C., pp. 92-98.


Title Object extraction using genetic algorithms and morphological processing
Author(s) Zheng, Hong
Pan, Li
Nahavandi, Saeid
Conference name Society of Photo-optical Instrumentation Engineers (2002 : Shanghai, China)
Conference location Shanghai, China
Conference dates 16-17 October 2002
Title of proceedings SPIE 2002 : Color science and imaging technologies : 16-17 October, 2002, Shanghai, China
Editor(s) Zhao, DaZun
Luo, Ming Ronnier
Aizawa, Kiyoharu
Publication date 2002
Series Proceedings of SPIE--the International Society for Optical Engineering ; v. 4922
Start page 92
End page 98
Publisher SPIE
Place of publication Washington, D.C.
Summary This paper introduces a novel methodology for object detection using genetic algorithms and morphological processing. The method employs a kind of object oriented structuring element, which are derived using genetic algorithm operating. The population of morphological filters iteratively evaluated according to a statistical performance index corresponding to object extraction ability, and evolves into an optimal structuring elements using the evolution principles of genetic search. Experimental results of object extraction in high resolution satellite images are presented to illustrate the merit and feasibility of the proposed method.
Language eng
Field of Research 090905 Photogrammetry and Remote Sensing
HERDC Research category E2 Full written paper - non-refereed / Abstract reviewed
Copyright notice ©2002, SPIE
Persistent URL http://hdl.handle.net/10536/DRO/DU:30013866

Document type: Conference Paper
Collection: School of Engineering and Technology
Connect to link resolver
 
Unless expressly stated otherwise, the copyright for items in Deakin Research Online is owned by the author, with all rights reserved.

Versions
Version Filter Type
Citation counts: TR Web of Science Citation Count  Cited 0 times in TR Web of Science
Access Statistics: 371 Abstract Views  -  Detailed Statistics
Created: Tue, 21 Oct 2008, 14:15:44 EST