Computer Engineering and Applications ›› 2011, Vol. 47 ›› Issue (15): 219-221.

• 图形、图像、模式识别 • Previous Articles     Next Articles

Edge detection of crack defect based on wavelet multi-scale multiplication

JIA Chao,WANG Yaokun,XING Jingjing   

  1. College of Information Science and Engineering,Yanshan University,Qinhuangdao,Hebei 066004,China
  • Received:1900-01-01 Revised:1900-01-01 Online:2011-05-21 Published:2011-05-21


贾 超,王耀坤,邢晶晶   

  1. 燕山大学 信息科学与工程学院,河北 秦皇岛 066004

Abstract: A new image edge detection algorithm which is based on wavelet transform is concerned with doing multi-scale wavelet decomposition to the image with multi-scale of edge information and the modulus maximum value of wavelet transform,and then making a multiplication of consecutive scale wavelet coefficient to enhance edge and achieving the final image edge with double threshold to remove noise components.The result of test indicates that this algorithm solves problems of edge noise and the bad edge,and ensures the accuracy of edge continuation and positioning.The algorithm with double threshold is superior to a single threshold and can be used effectively in framing member detection.

Key words: edge detection, wavelet transform, multi-scale, scale multiplication, double threshold value



关键词: 边缘检测, 小波变换, 多尺度, 尺度积, 双阈值