An Automatic Detection by Classification of Cracked Pixels or Noncracked Pixels in Road Surface

Khaddouj Taifi,Naima Taifi,Es-Said Azougaghe,Said Safi,Andres Saez

doi:10.1155/2021/3151460

Khaddouj Taifi, Naima Taifi + Show 3 more

Open Access

https://doi.org/10.1155/2021/3151460

Copy DOI

Abstract

Automatic detection and monitoring of the condition of cracks in the road surface are essential elements to ensure road safety and quality of service. A crack detection method based on wavelet transforms (2D-DWT) and Jerman enhancement filter is used. This paper presents different contributions corresponding to the three phases of the proposed system. The first phase presents the contrast enhancement technique to improve the quality of roads surface image. The second phase proposes an effective detection algorithm using discrete wavelet (2D-DWT) with “db8” and two-level sub-band decomposition. Finally, in the third phase, the Jerman enhancement filter is usually used with different parameters of the control response uniformity “ τ ” to enhance for cracks detection. The experimental results in this article provide very powerful results and the comparisons with five existing methods show the effectiveness of the proposed technique to validate the recognition of surface cracks.

Highlights

Amet et al [12] presented a method for edge defect detection based on wavelet decomposition and cooccurrence as a descriptor to extract the characteristics of the images to classify the images as defective or nondefective
Mathematical morphology [15, 16] can be used in automatic crack detection system [17] using a process based on Jensen– Shannon divergence and wavelet for detection of the crack
Nguyen et al [22] proposed a new approach by applying an anisotropy (FFA) of automatic crack detection. e proposed method using two-dimensional wavelet (2D-DWT) and Jerman enhancement filter gives good performance contrary of the M1 [23] and M2 [20], Gc [21], FFA [22], and MPS [24] methods

Summary

Introduction

Amet et al [12] presented a method for edge defect detection based on wavelet decomposition and cooccurrence as a descriptor to extract the characteristics of the images to classify the images as defective or nondefective. In the relay metal plate, Aswini et al [14] used the bottom-hat transform filtering approach and mathematical morphology to detect the surface cracks. Zalama et al [19] developed a method based on the Gabor filters to detect the transverse and longitudinal cracks. As a complete method to develop an automatic crack detection system, Chambon and Moliard [20] presented an approach based on a multiscale extraction and a Markovian segmentation addresses the problem of automatic crack detection. Nguyen et al [22] proposed a new approach by applying an anisotropy (FFA) of automatic crack detection. Is paper is organized as follows: Section 2 presents a diagram that contains a method of detecting and extracting cracked pixels or noncracked pixels on the road surface.

Methods

Results

Conclusion