A method of multi-scale edge detection based on lifting scheme and fusion rule

Author

Ge, Wen ; Gao, Li-Qun ; Sun, Qing

Author_Institution

Northeastern Univ., Shenyang

Volume

2

fYear

2007

fDate

2-4 Nov. 2007

Firstpage

952

Lastpage

955

Abstract

Recently, the edge detection methods based on wavelet transform are mainly to extract image edge of high-frequency parts and to ignore some edge information of low-frequency ones. And the traditional wavelet transform is time and memory consuming. Therefore a method of multi-scale edge detection based on lifting scheme and fusion rule is proposed in this paper. This algorithm should be carried out first to decompose the source image by lifting scheme. Then the edges of high-frequency and low-frequency sub-images are extracted separately. The final edge image is obtained through the fusion rule of average energy. Experimental results showed that the algorithm has advantages of quick operation, efficient suppression of noise and high detection accuracy.

Keywords

edge detection; feature extraction; image denoising; image fusion; wavelet transforms; feature extraction; fusion rule; lifting scheme; multiscale edge detection; noise suppression; wavelet transform; Agricultural engineering; Data mining; Frequency domain analysis; Image analysis; Image edge detection; Image processing; Information analysis; Low-frequency noise; Wavelet analysis; Wavelet transforms; Canny operator; fusion rule; lifting scheme; multi-scale edge detection; wavelet transform;

fLanguage

English

Publisher

ieee

Conference_Titel

Wavelet Analysis and Pattern Recognition, 2007. ICWAPR '07. International Conference on

Conference_Location

Beijing

Print_ISBN

978-1-4244-1065-1

Electronic_ISBN

978-1-4244-1066-8

Type

conf

DOI

10.1109/ICWAPR.2007.4420807

Filename

4420807