Based on soft-threshold wavelet de-noising combining with Prewitt operator edge detection algorithm
This article describes the commonly used edge detection operator (Including the Roberts operator, Sobel operator, Prewitt operator, Laplacian operator, as well as the Canny operator) of the basic principles, and its performance is analyzed and evaluated. Since traditional edge detection operator in the image containing Gaussian white noise when there is obvious shortcomings, this paper presents a based on soft-threshold wavelet de-noising combining with the Prewitt operator edge detection algorithm. This algorithm has the characteristics of wavelet multi-resolution, overcoming the traditional neighborhood selection algorithm for noise suppression and edge positioning accuracy of the contradictions, but also with a wavelet transform the role of band-pass filter, through the soft-threshold de-noising methods in the various to remove lowamplitude noise and the undesired signals, combined with Prewitt operator airspace convolution properties that can accurately detect the image edge and effective noise suppression effect of signal detection.
edge detection Hard-threshold de-noising soft-threshold de-noising wavelet transform median filter Prewitt operator
Wenshuo Gao Lei Yang Xiaoguang Zhang Bin Zhou Chunxi Ma
Information Engineering School of Communication University of China
国际会议
上海
英文
155-162
2010-06-22（万方平台首次上网日期，不代表论文的发表时间）