DocumentCode
3154508
Title
An improved Kirsch human face image edge-detection method based on canny lgorithm
Author
Wei-bo, Yu ; Zun-sheng, Du
Author_Institution
Sch. of Electr. & Electron Eng., Changchun Univ. of Technol., Changchun, China
fYear
2011
fDate
16-18 April 2011
Firstpage
4740
Lastpage
4743
Abstract
In view of the Kirsch edge detection algorithm´s shortage, a method of improved Kirsch human face edge detection was proposed. First, this method smoothed the original image with Gaussian filter, calculated its gradient image. Then, this method calculated the gradient image using the improved Kirsch algorithm, and extract edge according T1 and T2 two. Computer simulation experiments indicated that the improved method is not susceptible to Noises, and it could detect weak edge. The result of the experiments showed that the effect of the improved method is super to the classical Kirsch edge detection method.
Keywords
Gaussian processes; edge detection; face recognition; filtering theory; Canny algorithm; Gaussian filter; computer simulation experiments; gradient image; improved Kirsch human face image edge detection method; Face; Gray-scale; Humans; Image edge detection; Noise; Pixel; Smoothing methods; Canny algorithm; Kirsch algorithm; edge detection; face recognition;
fLanguage
English
Publisher
ieee
Conference_Titel
Consumer Electronics, Communications and Networks (CECNet), 2011 International Conference on
Conference_Location
XianNing
Print_ISBN
978-1-61284-458-9
Type
conf
DOI
10.1109/CECNET.2011.5768553
Filename
5768553
Link To Document