Road crack detection using adaptive multi resolution thresholding techniques

TELKOMNIKA, Vol.17, No.4, August 2019, pp.1874~1881
ISSN: 1693-6930, accredited First Grade by Kemenristekdikti, Decree No: 21/E/KPT/2018
DOI: 10.12928/TELKOMNIKA.v17i4.12755  1874
Received November 5, 2018; Revised January 28, 2019; Accepted March 1, 2019
Road crack detection using adaptive multi resolution
thresholding techniques
Zuraini Othman*
1
, Azizi Abdullah
2
, Fauziah Kasmin
3
, Sharifah Sakinah Syed Ahmad
4
1,3,4
Department of Intelligent Computing and Analytics,
Faculty of Information & Communication Technology, Universiti Teknikal Malaysia Melaka,
Hang Tuah Jaya, 76100 Durian Tunggal, Melaka, Malaysia
2
Center for Artificial Intelligence Technology, Faculty of Information Science and Technology,
Universiti Kebangsaan Malaysia 43600 Bangi, Selangor Darul Ehsan, Malaysia
*Corresponding author, e-mail: zuraini@utem.edu.my
1
, azizia@ukm.edu.my
2
,
fauziah@utem.edu.my
3
, sakinah@utem.edu.my
4
.
Abstract
Machine vision is very important for ensuring the success of intelligent transportation systems,
particularly in the area of road maintenance. For this reason, many studies had been focusing on
automatic image-based crack detection as a replacement for manual inspection that had depended on
the specialist’s knowledge and expertise. In the image processing technique, the pre-processing and edge
detection stages are important for filtering out noises and in enhancing the quality of the edges in
the image. Since threshold is one of the powerful methods used in the edge detection of an image, we
have therefore proposed a modified Otsu-Canny Edge Detection Algorithm in the selection of the two
threshold values as well as implemented a multi-resolution level fixed partitioning method in the analysis of
the global and local threshold values of the image. This is then followed by a statistical measure in
selecting the edge image with the best global threshold. This study had utilized the road crack image
dataset that were obtained from Crackforest. The results had revealed the proposed method to not only
perform better than the conventional Canny edge detection method but had also shown the maximum
value derived from the local threshold of 5x5 partitioned image outperforming the other partitioned scales.
Keywords: edge detection, fixed partitioning, machine vision, multi-resolution level, road crack detection
Copyright © 2019 Universitas Ahmad Dahlan. All rights reserved.
1. Introduction
The machine vision technology has been growing rapidly owing to the many benefits
it offers to the manufacturers such as the automation of quality monitoring and providing
the advantage of a more accurate evaluation system. For this reason, the application
of computer vision techniques had been proven to be particularly useful for the transport and
highways departments in automatically detecting and assessing patches, potholes and road
pavement cracks. There had been many studies conducted on crack detection, not only on
pavements, but also in glass, ceramics, tiles and tunnels [1–7]. Some of the most commonly
edge detection techniques used are the Canny, Sobel, Prewitt and Robert methods.
The pre-processing stage is considered to be one of the key steps in the distress detection
system, where it eases the cracking detection through noise suppression and the sharpening of
the linear features in the raw images that are usually associated with the crack features. In
general, the basic approach is made up of a pre-processing step along with the distress or road
cracks detection module. However, these systems tend to provide incorrect reports on
the cracking of the boundaries that correspond to non-crack elements such as joints, patches
and road markings. As such, to prevent these false crack detections from taking place, a
specific non-crack features stage is required to mask the region of the images where non-crack
features have been detected [8].
Edge detection is an image processing technique for finding the boundaries of objects
within images by detecting the intensity discontinuities in a digital image. This method is
commonly used for image segmentation and data extraction in areas such as image processing,
computer vision, and machine vision. In the case of image thresholding, it is a simple, yet
effective way of partitioning an image into a foreground and background and can be regarded
as a type of image segmentation that isolates objects by converting the greyscale images into

TELKOMNIKA ISSN: 1693-6930 
Road crack detection using adaptive multi resolution thresholding techniques (Zuraini Othman)
1875
binary images. There had been studies conducted on both edge-based and threshold-based
segmentation such as the Canny edge detection and Otsu thresholding methods [9–11].
The Otsu method is based on grey level histograms that are deduced by using the least square
method and is currently regarded as the most stable technique used for image threshold
segmentation. From a statistical perspective, this method also generates the best threshold
value [12], which is one of the key factors that greatly affect the performance of the traditional
Canny Operator. As such, this research had followed the method used from previous studies
such as [12–18], which is to provide an improved self-adaptive threshold Canny Operator that
inherits the merit of Otsu method in choosing the low threshold (Lt) and high threshold (Ht)
values adaptively.
The selection of a threshold value is vital in ensuring that an accurate edge is given,
which not only produces a clear image of the cracks, but also to filter out the cracks from other
layers as layerwise instead of laminate-wise. The length and location of each individual crack is
then measured from the filtered images by using a simple heuristic procedure [7]. In cement,
the crack patterns are detected by using a combination of threshold and filter-like edge
detection methods, which is similar to the method Sobel had used in detecting cracks within
a binary image. By utilizing a suitable threshold binary image, the pixels are categorized into
the foreground and the background image and the residual noise is eliminated through the use
of Sobel’s ﬁltering. After undergoing the filtering process, the Otsu method is then used to
detect the major cracks. This detection method had been discussed earlier in [2].
The modified Canny edge detection algorithm had been used in a few studies
such as [19]. Since edge preserving filters are used in the applications of road cracks detection,
this algorithm was therefore tested on randomly chosen pavement images data.
While the traditional Canny edge detection method had provided a relatively simple but precise
methodology for edge detection problem, the Gaussian filter that was used to smooth
the images, however, had caused the loss of edge information during noise suppression.
As such, the Mallat wavelet transform was therefore proposed to reinforce the weak edges of
the input images and quadratically optimising the genetic algorithm to obtain a suitable
threshold in self-adapting standard when performing the Canny algorithm steps. As a result,
this newly improved Canny model had met the needs for real-time road cracks detection and
had compensated the disadvantages of a traditional Canny algorithm by effectively and rapidly
identifying road cracks in a short amount of time.
As mentioned earlier, the Otsu method is generally used in the conventional Canny
method to adaptively find the high and low threshold values. Much research has been done on
the modification of the Canny method by using the Otsu method such as the fixed partitioning
technique that was used for the global and local threshold analysis of the image. By using
this approach, the image is divided into several equal portions, where the local histogram for
each of the respective part is then calculated. One of the main advantages of using this method
is that it provides an additional input to the histogram as a way of obtaining the spatial
distribution of the image content [20]. This proposed method had used a comprehensive
technique in generating edge images. [21] had discussed how the Salient Detection method can
be utilised for crack detection. Visually, salient regions are more conspicuous because they are
in contrast with the surroundings. Although the current methods had illustrated their efficacy for
the detection of salient areas in the Berkeley database [22], they had demonstrated poor
performance in terms of the continuity and completeness of the detected crack. In [15], since
the modified Canny method had demonstrated effective detection within the Berkeley database,
this algorithm was adopted for this study but with certain modifications.
This paper had proposed an algorithm for finding edge images within the CrackForest
dataset [21] through the use of an adaptive threshold approach, which is based on a local value
after the fixed partitioning of the image in five different levels. While the high threshold value (Ht)
was obtained through the use of Otsu method, the low (Lt) threshold value on the other hand,
was determined by halving the high threshold value. Contrary to [14], the three statistical
measures, namely the minimum, maximum, and mean values from all the Lt and Ht are
generated. These are the measurements from the best obtained edge images that had been
compared with the ground truth images provided by the dataset. The outcomes from
the experiment were then compared against the results obtained from the Canny method.
Based on the comparison results, it was revealed that the proposed method had provided edge
images with the best accuracy level. The following sections of this paper will provide a detailed

 ISSN: 1693-6930
TELKOMNIKA Vol. 17, No. 4, August 2019: 1874-1881
1876
discussion on the materials and methods used for the research, an explanation of
the experimental and comparison results as well as the conclusion of the study conducted.
2. Materials and Methods
This paper had proposed a road crack detection algorithm that consisted of
the following steps: image retrieval and pre-processing, road crack detection and finally,
the analysis of the performance measurement shown in Figure 1.
Figure 1. Flowchart of the proposed road crack detection algorithm
2.1 Image Pre-Processing
Here, the algorithm of the pre-processing phase in [23] is adopted to get a clearer crack
edge of road images. At this stage, the image will undergo several manipulations such as pixel
smoothing, normalisation, white line detection and saturation before the crack is detected.
Figure 2 shows the original image and the pre-processed image with its grey level histogram.
(a) (b)
Figure 2. Sample of the (a) original image and (b) the smoothed image with
its grey level histogram
2.2 Crack Detection Using Adaptive Multi Resolution Thresholding Techniques
After the original images had been retrieved in grey level image format and subjected to
the pre-processing phase, the fixed partitioning is then carried out to separate the image into
five different levels. While implementing the Canny edge detection [24], the Otsu method [9] is
adopted in the selection of the threshold values. However, a few changes had to be made in
order to obtain the best low threshold (Lt) and high threshold values (Ht) as shown in [14, 15]
through the utilisation of different image resolutions. At this stage, the global and local spatial
values will be selected from the variance values depicted in the 2x2 partition (CO2x2),
3x3 partition (CO3x3), 4x4 partition (CO4x4) and 5x5 partition (CO5x5). Next, the local
threshold values for each of the partition are used to generate a global edge image shown in
Figure 3. Unlike the previous studies, the global threshold values from CO2x2, CO3x3, CO4x4
and CO5x5 are then applied into the statistical measures to determine the portion that gives
the most accurate minimum (min), maximum (max) and average (mean) values.
Image
retrieved
Analysis of
performance
measurement
Image
pre-processing
Crack detection using adaptive
multi resolution thresholding
techniques

1877
Let’s assume the fixed partitioning for each of the resolution as such:
𝐿1,1 ∈ COG (1)
𝐿2,1, 𝐿2,2, 𝐿2,3 and 𝐿2,4 ∈ CO2×2 (2)
𝐿3,1, 𝐿3,2, 𝐿3,3, 𝐿3,4, 𝐿3,5, 𝐿3,6, 𝐿3,7, 𝐿3,8 and 𝐿3,9 ∈ CO3×3 (3)
𝐿4,1, 𝐿4,2, 𝐿4,3, 𝐿4,4, 𝐿4,5, 𝐿4,6, 𝐿4,7, 𝐿4,8, 𝐿4,9, 𝐿4,10, 𝐿4,11, 𝐿4,12, 𝐿4,13, 𝐿4,14, 𝐿4,15 and
𝐿4,16 ∈ CO4×4 (4)
𝐿5,1, 𝐿5,2, 𝐿5,3, 𝐿5,4, 𝐿5,5, 𝐿5,6, 𝐿5,7, 𝐿5,8, 𝐿5,9, 𝐿5,10, 𝐿5,11, 𝐿5,12, 𝐿5,13, 𝐿5,14, 𝐿5,15, 𝐿5,16,
𝐿5,17, 𝐿5,18, 𝐿5,19, 𝐿5,20, 𝐿5,21, 𝐿5,22, 𝐿5,23, 𝐿5,24 and 𝐿5,25 ∈ CO5×5 (5)
Figure 3. The process used in the adaptive multi-resolution thresholding technique
for edge detection

 ISSN: 1693-6930
1878
here, each of the fixed partitioning is represented as 𝐿𝑖,𝑗 with 𝑖 = partition involved and
𝑗 = 1, 2, … , 𝑖2
. The statistical measures for each of the resolution level at high (RHt) and low
threshold values (RLt) for min, max and mean are defined as such:
RHt =
1
n
× arg max(Ht ∈ Li,j) and RLt =
1
n
×arg max(Lt ∈ Li,j) (6)
RHt =
1
n
× arg min(Ht ∈ Li,j) and RLt =
1
n
×arg min(Lt ∈ Li,j) (7)
RHt =
1
n
× mean(Ht ∈ Li,j) and RLt =
1
n
× mean(Lt ∈ Li,j) (8)
where weight 𝑛 = 1,2,3, … ,10.
2.3 Performance Measurement
At this stage, each of the obtained edge detection images will be compared against
the ground truth image. The measurements as discussed in [25] are then used in
the result’s analysis:
Recall =
True Positive
True Positive + False Negative
(9)
Precision =
True Positive
True Positive + False Positive
(10)
FMeasure = 2 ×
Precision × Recall
Precision + Recall
(11)
3. Experiment and Results
This study had utilized the provided CrackForest dataset [21] and ground truth edge
images. The FMeasure results that are shown in Figure 4 had been obtained by using [14, 15]
algorithms after the pre-processing phase [23]. There were fifty results obtained for each of
the statistical measure, namely, min from (6), max from (7) and mean from (8), for each of the n
used. As shown in Figure 4 (a)(i), Figure 4 (b)(i), Figure 4 (a)(ii) and Figure 4 (b)(ii),
the corresponding CrackForest dataset results from 𝑛 = 1 and the max value from (7) had
yielded dominant values for each of the edge image generated.
Table 1 shows the FMeasure results of the 10 images used, where the value for CO5x5
was shown to be higher than the conventional Canny method and the other levels of resolution
used. Although the edge image that was obtained for image 001 shown in Figure 5 had
generated noise by using the Canny method, it did not display any visible differences from
the edge images obtained in COG, CO2x2, CO3x3, CO4x4 and CO5x5. The average results
from the dataset used had also shown the accurate edge image generated by CO5x5 shown in
Table 2. In Figure 6, by comparing the edge image obtained from the Canny method, there is a
clear indication that the image produced by the proposed method had been similar to
the ground truth image. From all of the obtained images and results for road cracks, we have
found (12) to provide the most favourable result:
RHt = arg max(Ht ∈ Li,j) and RLt = arg max(Lt ∈ Li,j) (12)
Table 1. F-Measure Max Results on 10 Images from
Crackforest Dataset
Method Canny COG CO2x2 CO3x3 CO4x4 CO5x5
001 86.35352 99.45778 99.45812 99.46042 99.46075 9 .46075
002 88.56953 98.98639 99.00228 99.00448 99.01731 99.01731
003 88.4293 99.43131 99.44877 99.45173 99.45173 99.45173
004 89.52685 99.3298 99.3298 99.33016 99.34008 99.34008
005 89.55255 99.43277 99.44134 99.44233 99.44299 99.44299
006 86.88847 99.19375 99.30702 99.33511 99.30702 99.33511
007 88.23459 99.4437 99.46317 99.46415 99.46449 99.46449
008 89.09414 99.31765 99.31865 99.31898 99.31931 99.32427
009 87.2423 99.09312 99.1823 99.2214 99.22239 99.22239
010 87.91355 99.443 99.44465 99.44597 99.44597 99.46378

1879
(a)(i) (a)(ii)
(b)(i) (b)(ii)
Figure 4. Results obtained on two images: (a) image 001 and (b) image 002, Results
(i) for 𝑛 = 1,2,3 … ,10 and (ii) for min, max and mean for 𝑛 = 1 only
(a) (b) (c) (d)
(e) (f) (g) (h)
Figure 5. (a) Original image, (b) Ground truth image, which is followed by the edge image
generated by (c) Canny method, (d) COG, (e) CO2x2, (f) CO3x3, (g) CO4x4 and (h) CO5x5

 ISSN: 1693-6930
1880
Table 2. The F-Measure Values that were Obtained from the Average Max
Method Average
Canny 87.80299
COG 99.29134
CO2x2 99.31586
CO3x3 99.3238
CO4x4 99.32689
CO5x5 99.33232
(a) (b) (c) (d)
Figure 6. (a) Original image, (b) Ground truth image, which is followed by the edge image
generated by (c) Canny method and (d) the proposed method
4. Conclusion
This study had proposed a new crack detection method through the application of
Otsu-Canny Edge Detection Algorithm as well as incorporating calculations in the global and
local threshold analysis of the fixed partitioned images at multiple resolution levels. To obtain
the optimal threshold value, a sampling approach was utilised in the calculation of statistical
measures, namely the minimum, maximum and mean values from the class variance of each
partitioned image. The most accurate image is then selected based on the resolution level,
statistical measure and the weight used.
Based on the results obtained from the CrackForest image datasets, the proposed
method was found to perform better than the Canny method in terms of its edge image results
and the F-Measure values. In this study, although the modified version of the Canny method
had resulted in the detection of unwanted edges, it was still selected as the edge images had
provided the most complete edge boundaries. The local spatial adaptive approach through
the use of Otsu method was also proven to enhance the edges by eliminating the noise
acquired from the conventional Canny method. The results had reflected more accurate edge
images as it had taken in the foreground image of interest and ignored the background regions.
Acknowledgements
The deepest gratitude and thanks to Universiti Teknikal Malaysia Melaka (UTeM)
in supporting this research PJP/2018/FTMK(2B)/S01629.

1881
References
[1] Li X, Jiang H, Yin G. Detection of surface crack defects on ferrite magnetic tile. NDT & E
International. 2014; 62: 6–13.
[2] Talab AMA, Huang Z, Xi F, Haiming L. Detection crack in image using Otsu method and multiple
filtering in image processing techniques. Optik (Stuttg). 2016; 127(3): 1030–1033.
[3] Hu Y, Zhao CX, Wang HN. Automatic pavement crack detection using texture and shape descriptors.
IETE Technical Review. 2010; 27(5): 398–405.
[4] Anwar SA, Abdullah MZ. Micro-crack detection of multicrystalline solar cells featuring an improved
anisotropic diffusion filter and image segmentation technique. Eurasip J. Image Video Process. 2014;
2014(1): 1–17.
[5] Kabir S. Imaging-based detection of AAR induced map-crack damage in concrete structure. NDT & E
International. 2010; 43(6): 461–469.
[6] Yiyang Z. The design of glass crack detection system based on image preprocessing technology. Inf.
Technol. Artif. Intell. Conf. (ITAIC). 2014: 39–42.
[7] Glud JA, Dulieu-Barton JM, Thomsen OT, Overgaard LC. Automated counting of off-axis tunnelling
cracks using digital image processing. Compos. Sci. Technol. 2016; 125: 80–89.
[8] Gavilán M, et al. Adaptive road crack detection system by pavement classification. Sensors. 2011;
11(10): 9628–9657.
[9] Otsu N. A threshold selection method from gray-level histograms. IEEE transactions on systems,
man, and cybernetics. 1979; 9(1): 62–66.
[10] Al-Kubati AAM, Saif JAM, Taher MAA. Evaluation of Canny and Otsu image segmentation.
International Conference on Emerging Trends in Computer and Electronics Engineering.
2012: 23–25.
[11] Anitha R, Jyothi S, Mamatha DM. Classifying Penaeid Prawns Species using Canny and Otsu.
Int. J. Adv. Res. Comput. Sci. Manag. Stud. 2014; 2(11): 35–42.
[12] Fang M, Yue G, Yu Q. The study on an application of otsu method in canny operator. Proceedings.
The 2009 International Symposium on Information Processing (ISIP 2009). 2009; 2(4): 109–112.
[13] Zhao J, Yu H, Gu X, Wang S. The edge detection of river model based on self-adaptive Canny
Algorithm and connected domain segmentation. 2010 8th World Congr. Intell. Control Autom. 2010;
2(1): 1333–1336.
[14] Othman Z, Abdullah A. An Adaptive Threshold Based On Multiple Resolution Levels for Canny Edge
Detection. IRICT 2017 Recent Trends Inf. Commun. Technol. 2017: 316–323.
[15] Othman Z, Abdullah A, Prabuwono AS. A statistical approach of multiple resolution levels for Canny
edge detection. 2012 12th International Conference on Intelligent Systems Design and Applications
(ISDA). 2012: 837–841.
[16] Jie G, Ning L. An Improved Adaptive Threshold Canny Edge Detection Algorithm. 2012 Int. Conf.
Comput. Sci. Electron. Eng. 2012: 164–168.
[17] Hui P, Ruifang Z, Shanmei L, Youxian W, Lanlan W. Edge Detection of Growing Citrus Based on
Self-Adaptive Canny Operator. 2011 Int. Conf. Comput. Distrib. Control Intell. Environ. Monit. 2011:
342–345.
[18] Kasmin F, Othman Z, Ahmad SS. Automatic Road Crack Segmentation Using Thresholding Methods.
International Journal of Human and Technology Interaction (IJHaTI). 2018; 2(2): 75–82.
[19] Zhao H, Qin G, Wang X. Improvement of canny algorithm based on pavement edge detection.
Proc.-2010 3rd Int. Congr. Image Signal Process CISP 2010. 2010; 2: 964–967.
[20] Abdullah A, Veltkamp RC, Wiering MA. Spatial pyramids and two-layer stacking SVM classifiers for
image categorization: A comparative study. Proc. Int. Jt. Conf. Neural Networks. 2009: 5–12.
[21] Shi Y, Cui L, Qi Z, Meng F, Chen Z. Automatic road crack detection using random structured forests.
IEEE Transactions on Intelligent Transportation Systems. 2016; 17(12): 3434–3445.
[22] Martin D, Fowlkes C, Tal D, Malik J. A database of human segmented natural images and its
application to evaluating segmentation algorithms and measuring ecological statistics. Proceedings
Eighth IEEE International Conference on Computer Vision. ICCV 2001. 2001; 2: 416–423.
[23] Oliveira H, Correia PL. CrackIT—An image processing toolbox for crack detection and
characterization. 2014 IEEE international conference on image processing (ICIP). 2014: 798–802.
[24] Canny J. A Computational Approach to Edge Detection. IEEE Trans. Pattern Anal. Mach. Intell. 1986;
PAMI-8(6): 679–698.
[25] Powers DM. Evaluation: From Precision, Recall and F-Measure To Roc, Informedness, Markedness
& Correlation. J. Mach. Learn. Technol. 2011; 2(1): 37–63.

Road crack detection using adaptive multi resolution thresholding techniques

More Related Content

What's hot (20)

Similar to Road crack detection using adaptive multi resolution thresholding techniques (20)

More from TELKOMNIKA JOURNAL (20)

Recently uploaded (20)

Road crack detection using adaptive multi resolution thresholding techniques