Partial Differential Equation‐Based Enhancement and Crack Detection

Abstract

This paper presents an effective partial differential equation- (PDE-) based preprocessing algorithm for automated image-based crack detection. The proposed formulation combines various relevant and multiple processes such as contrast and selective edge enhancement in addition to edge-preserving smoothing to enhance the image prior to detection. The approach is adaptive and controlled by reliable image metrics to determine the stopping time of the PDE ensuring optimum results for various images. Additionally, a simplified thresholding algorithm based on local global maximum gradient matching is used to extract the crack features from the image. The proposed scheme does not require arbitrary or manually tuned parameters nor a large dataset for training to obtain good results. Experiments indicate that the proposed approach performs better when compared to several other algorithms in the literature.

Automated crack segmentation via saturation channel thresholding, area classification and fusion of modified level set segmentation with Canny edge detection

“…Other methods involve free form anisotropy (FFA) [ 18 ], pixel refinement [ 19 ], random forests [ 20 ], percolation [ 21 ], fusion methods [ 22 ] and work by Kong and Li [ 23 ]. Recently, methods utilizing partial differential equations (PDEs) have been reported in the literature [ 8 , 9 , 24 , 25 ]. These PDE-based algorithms employed Anisotropic Diffusion (AD) [ 25 ], forward and backward Diffusion (FABD) [ 8 , 24 ] and Total Variation Regularization (TVR) [ 9 ].…”

“…Recently, methods utilizing partial differential equations (PDEs) have been reported in the literature [ 8 , 9 , 24 , 25 ]. These PDE-based algorithms employed Anisotropic Diffusion (AD) [ 25 ], forward and backward Diffusion (FABD) [ 8 , 24 ] and Total Variation Regularization (TVR) [ 9 ]. In the proposed work, we utilize the shock filter [ 26 ] to achieve faster smoothing and sharpening in the image.…”

“…In previous work, we encountered problems when segmenting images of complex crack patterns on rough concrete surfaces [ 8 ]. Attempts from basic thresholding to combined smoothing and edge detection failed for such images.…”

“…We first convert the image to grayscale if it is an RGB colour image to reduce data and processing time. Then we perform illumination correction using a previously developed fuzzy homomorphic enhancement algorithm [ 8 , 55 , 56 ]. This allows the normalization of illumination without any edge or noise enhancement.…”

An Overview of Challenges Associated with Automatic Detection of Concrete Cracks in the Presence of Shadows

“…Some recent techniques use conventional pre-processing schemes for crack identification in rough concrete surfaces with a complex pattern of cracks. The crack identification technique proposed in [5] is based on an adaptive PDE-based pre-processing algorithm for concrete crack images. The implementation of this technique is combined with a local maximum-based thresholding scheme.…”