Research on feature extraction algorithm of pavement disease

In order to improve the accuracy and robustness of pavement crack image segmentation, an adaptive image enhancement algorithm is proposed. Based on the histogram of the disease image, linear transformation and equalization are performed to enhance the gray features. The image is divided into high and low frequency sub bands by using non subsampled contourlet transform, and the detail features are enhanced by using sigmoid function. At the same time, the corresponding adaptive order adjustment model and edge extraction algorithm are constructed to obtain the binary feature image. The experimental results show that the proposed algorithm has strong de-noising ability and can extract pavement crack features well. Compared with the traditional methods such as region growing and watershed, it has the advantages of fast speed and high accuracy.