Edge Detection Method of Pantograph Carbon Slide Plate Based on Wavelet and Curvelet Transform
In order to solve the problems of noise suppression and insufficient edge in the process of edge detection of pantograph carbon slide plate of electric multiple units,a new method is proposed.Firstly,the original image is subjected respectively to wavelet transform and curvelet transform,so as to obtain the enhanced images.Then,after multiple comparisons,the enhanced images are fused at a ratio of 0.9:0.1 to obtain the best fusion effect.In this way,a new image is obtained.Finally,the Canny operator is used to perform edge detection on the new image to obtain the final edge image.This method combines the advantages of wavelet transform and curvelet transform,which can not only effectively extract image singularity information in the whole frequency domain,but also have a good effect on curve singularity detection.It can describe the details and edge information of the image well,effectively improve the image clarity,and provide a guarantee for the quality of edge detection.By comparing with the edge detection results based on wavelet transform and curvelet transform,it is proved that the results obtained by the above detection method are better than the other two methods,and the edge extraction effect of pantograph slide plate is better.
NETL
NSTL
万方数据
