Improved Pavement Distress Detection Based on Contourlet Transform and Multi-direction Morphological Structuring Elements

摘要

Traditional methods for crack distress detection cannot capture the geometric information of images and tend to amplify noise. In order to solve this problem, an improved algorithm based on contourlet transform and multi-direction morphological structuring elements is proposed. The new algorithm decomposed image into approximation coefficients and detail coefficients. Morphological erode operations is used to distinguish noise form detail information according to dependencies of contourlet coefficients, then nonlinear mapping function is used to modify the contourlet coefficients. And the enhanced image is obtained by contourlet inverse transform. Compared with other traditional methods, the experimental results indicate that our method can effectively extract the edges of cracks and evidently decrease the influence of noises. Moreover, it can provide good image processing speed.