Pavement Crack Detection Based on Fractional Domain Adding Window and Contrast Enhancement

Qiuhao Zhou, Hongtu Zhao


The efficiency and accuracy of traditional artificial pavement crack detection are low. In this paper, the crack image is transformed into the fractional domain, and the fractional domain denoising is realized by windowing. Then, the fractional homomorphic filtering algorithm is used to enhance the contrast and obtain the highest contrast image under the optimal order. Finally, edge detection and threshold segmentation are performed on the image, and the crack edge is smoothed by doing or calculating, and then the crack characteristics in the crack image are effectively extracted by image morphology operation. Compared with the fractional frequency domain processing method and the improved HC method, the accuracy of the method is increased by 5.84 % and 4.5 %, and the recall rate is increased by 5.58 % and 3.52 %, respectively. It shows that the method has better detection effect and higher recognition rate in pavement crack detection.


Crack Detection; Fractional Fourier Transform; Fractional Domain Adding Window; Contrast Enhancement; Homomorphic Filtering

Full Text:


Included Database


Wang YH, Chen R. Image recognition method of pavement cracks based on fractional fourier transform and spectral enhancement [J]. Computer Applications, 2020, 40(S1): 189-194.

Zhang XM, Shen LS. Wavelet-based homomorphic filter for image contrast enhancement [J]. Chinese Journal of Electronics, 2001, 29(4): 531-533.

Jiang JR. Research on detection method and identification of pavement cracks based on image analysis[D]. Nanjing University of Posts and Telecommunications, 2016.

Li ZJ, Zhang CB, et al. Application of improved cosine window in harmonic analysis of virtual instruments[J]. Modern Electronic Technology, 2018, 41(15): 108-113.

Oppenheim AV, Schafer RW. Nonlinear filtering of multiplied and convolved signals. Proc. IEEE, 1968(56): 1264-1291.

Yu HC, Mu PA. Application of adaptive Canny algorithm in edge detection of steel plate defects [J]. Software Guide, 2018, 17(4):175-177.

Li SW, Li LC. Application of adaptive OSTU algorithm in ship edge detection and Its FPGA implementation [J]. Software Guide, 2019, 18(6): 176-180.

Zhong AE. Research on pavement crack recognition technology based on image processing [D]. Hubei: Wuhan University of Science and Technology, 2020.



  • There are currently no refbacks.

Copyright (c) 2022 Qiuhao Zhou, Hongtu Zhao

Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.