DocumentCode :
3420800
Title :
A new approach to estimate image blur extent based on wavelet module maximum
Author :
Zhang, Faquan ; Wang, Guofu ; Ye, Jingcai ; Liu, Qinghua ; Xiao, Xingda
Author_Institution :
Dept. of Inf. & Commun. Eng., Guilin Univ. of Electron. Technol., Guilin, China
fYear :
2010
fDate :
22-24 Oct. 2010
Firstpage :
193
Lastpage :
196
Abstract :
An approach to estimate image blur extent based on image edge width and wavelet module maximum was proposed. According to the definition of wavelet module value, three-order spline wavelet was chosen to implement multiscale wavelet edge detection and wavelet edge module values were obtained. To select half of wavelet edge module maximum as threshold to segment blur image and its binary image was obtained. Area and girth of the blur edge of the objects in the blur image were calculated according to pixel statistic principle. Blur edge width of objects in the image was given by area and girth of the transition edge. Image blur extent was determined by blur edge width. Experiment results show that the algorithm is effective and performs better.
Keywords :
edge detection; image segmentation; binary image; blur image segmentation; image blur extent estimation; image edge width; multiscale wavelet edge detection; pixel statistic principle; three-order spline wavelet; wavelet edge module maximum; wavelet edge module values; wavelet module maximum; Computers; Convolution; Image edge detection; Spline; Blur Edge Width; Image Blur Extent; Image Processing; Threshold Selection; Wavelet Module Maximum;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Intelligent Computing and Integrated Systems (ICISS), 2010 International Conference on
Conference_Location :
Guilin
Print_ISBN :
978-1-4244-6834-8
Type :
conf
DOI :
10.1109/ICISS.2010.5656816
Filename :
5656816
Link To Document :
بازگشت