摘要
利用小波变换模极大值法进行图像边缘检测时,需选择阈值,将小波变换系数较小的点滤掉,但是一幅图像中边缘的奇异性并不均匀,如果对变换后的图像取单一阈值,那么微弱边缘将会因为灰度不均匀、噪声等一并被滤除。针对这一问题,在上述算法中用双阈值法代替单阈值,使得图像边缘连续,同时也能很好地消除噪声,实验结果表明该算法简单实用,易于实现。
When using the modulus maximum value of wavelet transform in the image edge detection, we need choose appropriate threshold to filtrate the smaller point of the wavelet coefficient. However, the singularity of the edge in an image is not uniform; the faintness edge will be filtered with the non-uniform of gray-scale and noise, etc. In response to this problem, the use of dual-threshold method instead of a single threshold in the above algorithm will make the edge of the image in a row, as well as the elimination of noise can be very good. The results show that the algorithm is simple and practical, easy to implement.
出处
《装备制造技术》
2009年第4期47-48,共2页
Equipment Manufacturing Technology
关键词
小波变换
双阈值
边缘检测
wavelet transform
double threshold value
edge detection