PLUME EXTRACTION USING ENTROPIC THRESHOLDING AND REGION GROWING

NCUIR > College of Electrical Engineering & Computer Science > Graduate Institute of Electrical Engineering > journal & Dissertation > Item 987654321/29454

Please use this identifier to cite or link to this item: http://ir.lib.ncu.edu.tw/handle/987654321/29454

Title:	PLUME EXTRACTION USING ENTROPIC THRESHOLDING AND REGION GROWING
Authors:	TSENG,DC;SHIEH,WS
Contributors:	電機工程研究所
Keywords:	HISTOGRAM
Date:	1993
Issue Date:	2010-06-29 20:25:08 (UTC+8)
Publisher:	中央大學
Abstract:	An approach for extracting smoke plumes using entropic thresholding and region growing is proposed in this paper. First, the stack is located by an edge detector in an image. The stack location is taken to be a basic position for finding the plume. Several threshold values are then calculated using entropy measurement of the image based on a co-occurrence matrix. These threshold values are used to threshold the image into a lower-level image. A region-growing technique is applied to segment the thresholded image. Further processes are used to refine the segmented result. Finally, several features of the regions are derived using principal component analysis to extract the plume in the segmented image. We apply the approach to several examples to examine how it performs. The results indicate that the approach is a promising technique for plume extraction.
Relation:	PATTERN RECOGNITION
Appears in Collections:	[Graduate Institute of Electrical Engineering] journal & Dissertation

Files in This Item:

File	Description	Size	Format
index.html		0Kb	HTML	405	View/Open

社群 sharing