A fusion edge detection method based on improved Prewitt operator and wavelet transform

Abstract

The traditional Prewitt operator only has two detection templates of horizontal and vertical direction, edge detection accuracy is not high. In order to improve the edge detecting precision and computing speed, the traditional Prewitt operator is improved in this paper, the edge detecting operator is increased from two to four. But Prewitt operators are sensitive to noise, pseudo edge prone to detection, and the detecting method based on wavelet transform edge not only has good anti-noise, but also can preserve the edge details, this paper puts forward a kind of edge detecting algorithm based on wavelet transform and improved Prewitt operator edge image fusion: first the source image is processed by using median filter method, then the filtered image is enhanced by histogramequalizationmethod, the enhanced image is respectively detected bywavelet transform edge detection method and improved Prewitt operator edge detection method, finally the two edge detecting image is done image fusion by using wavelet image fusion algorithm based on adaptive wavelet image fusion algorithm, Experiments show that the fused image combines the advantages of two kinds of detection algorithm, the fusion detection method can suppress noise effectively, but also can improve the accuracy of edge detection. It is an ideal method of image edge detection.