An adaptive edge detection method is proposed for the sensitivity to noise and given threshold of existing Roberts algorithms. The basic principle of the Roberts algorithm is used and the direction of the detection is expanded. The algorithm generates automatically adaptive threshold according to the mean value of the 3×3 area pixels around the detecting pixel and the property of people's vision. It not only can keep advantages of existing Roberts algorithm such as parallel process
fast calculation speed and the comparatively thin edge
but also can play a certain part in restraining noise. Because the edge detected by Roberts algorithm is comparatively thick
and the efficiency of the edge-thin algorithm is lower
the edge-thin algorithm is analyzed and improved. The improved algorithm detects the edge of the image where there exists noise
filters the fake edge
then thins the edge of the image
and finally gets the single pixel edge. By comparing the test results of the adaptive edge detection algorithm with those of the existing Roberts algorithm
the adaptive edge detection method can generate automatically adaptive threshold
improves the performance in getting detailed-edge and restraining noise.
WANG Yueyue, WANG Qiuguang.A two-dimensional thresholding method based on the information of image edge [J]. Journal of Image and Graphics,2007,12(1):78-81.
MORRONE M C,NAVANGIONE A,BURR D. An adaptive approach to scale selection for line and edge detection [J].Pattern Recognition Letters,1995,16(7):667-677.
MALLAT S,HWANG W L. Singularity detection and processing with wavelets[J].Trans on Information Theory,1992,38(2):617-623.
AYDIN T. Multidirectional and multiscale edge detection via m-band wavelet transform [J].IEEE Trans on Image Processing,1996,5(9):1370-1377.
CANNY J. A computational approach to edge detection [J]. IEEE Trans on Pattern Analysis and Machine Intelligence,1986,8(6):679-698.
LENG Hanbing, WANG Xian, LIU Shangqian, et al. A neighborhood adaptive fuzzy enhancement algorithm based on human visual properties [J]. Opto-Electronic Engineering,2004,31(1):62-65.
WU Yingqian, FANG Tao, LI Congliang,et al. An approach for image enhancement based on wavelet analysis and properties of human visual system [J]. Journal of Data Acquisition Processing,2003,18(1):17-21.
LIU Yu, LI Yanjun, ZHANG Ke. A method of multi-pixels edge detecting of image [J]. Acta Photonica Sinica,2007,36(2):380-384.
ZHANG Renyan, ZHAO Guoling, SU Li. A new edge detection method in image processing [C]∥IEEE International Symposium on Communications and Information Technology.Piscataway,NJ,USA: IEEE, 2005:445-448.