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
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;
Conference_Titel :
Consumer Electronics, Communications and Networks (CECNet), 2011 International Conference on
Conference_Location :
XianNing
Print_ISBN :
978-1-61284-458-9
DOI :
10.1109/CECNET.2011.5768553