DocumentCode :
3528766
Title :
Edge detection via a fast and adaptive bidimensional empirical mode decomposition
Author :
Bhuiyan, Sharif M A ; Adhami, Reza R. ; Khan, Jesmin F.
Author_Institution :
Dept. of Electr. & Comput. Eng., Univ. of Alabama in Huntsville, Huntsville, AL
fYear :
2008
fDate :
16-19 Oct. 2008
Firstpage :
199
Lastpage :
204
Abstract :
This paper presents a new approach of edge detection utilizing bidimensional empirical mode decomposition (BEMD) technique. For this purpose a recently developed fast and adaptive BEMD (FABEMD) is employed to decompose the given image into several bidimensional intrinsic mode functions (BIMFs). In FABEMD, order statistics filters (OSFs) are employed to get the upper and lower envelopes in the decomposition process, instead of the surface interpolation, which enables fast decomposition and well characterized BIMFs. Since the first BIMF provides the highest local spatial variations and/or scales of the image, this BIMF is then processed for obtaining the edge. Binarization and morphological operations are applied as post processing operations to the first BIMF to achieve the desired edge map. The proposed method is compared with two other standard techniques namely, Canny and Sobel edge operators. Simulation results with real images demonstrate the efficacy of the proposed algorithm for edge detection.
Keywords :
edge detection; filtering theory; interpolation; multidimensional signal processing; FABEMD; bidimensional empirical mode decomposition; bidimensional intrinsic mode functions; edge detection; edge operators; fast and adaptive BEMD; local spatial variations; order statistics filters; real images; surface interpolation; Brightness; Filters; Image edge detection; Image resolution; Interpolation; Morphological operations; Object detection; Spatial resolution; Statistics; Surface morphology; Edge detection; binarization; fast and adaptive bidimensional empirical mode decomposition (FABEMD); morphological operators; order-statistics filter;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Machine Learning for Signal Processing, 2008. MLSP 2008. IEEE Workshop on
Conference_Location :
Cancun
ISSN :
1551-2541
Print_ISBN :
978-1-4244-2375-0
Electronic_ISBN :
1551-2541
Type :
conf
DOI :
10.1109/MLSP.2008.4685479
Filename :
4685479
Link To Document :
بازگشت