Published by : International Journal of Engineering Research & Technology (IJERT)

http://www.ijert.org ISSN: 2278-0181

Vol. 7 Issue 03, March-2018

Crack Detection Using Image Processing:Review

Prof. P. S. Yadav Jayesh Patil
Mechanical Engineering, Mechanical Engineering,
Sinhgad College of Engineering Sinhgad College of Engineering
Pune, India Pune, India
Pranit Patil
Mechanical Engineering,
Sinhgad College of Engineering
Pune, India
Vaibhav Lahane Hrishikesh Patil
Mechanical Engineering, Mechanical Engineering,
Sinhgad College of Engineering Sinhgad College of Engineering
Pune, India Pune, India

Abstract: The deterioration of structures due to cracks is Dijkstra’s algorithm, Neural Network, Statistical approach,
one of the major issues in large construction site, Segmentation are the process that have been focused in this
exclusively where manual inspection is not possible. In such literature. Softwares like image processing lab, Open CV and
cases, a novel idea is proposed which integrates an MATLAB Graphical User interface can be developed for easy
Unmanned Aerial Vehicle (UAV’s), image processing monitoring and real time inspection through which data can be
techniques and data acquisition which helps in monitoring extracted.
of construction. The stated purpose of using an UAV with Initially the structure of the image processing based crack
camera mounted on it is to reach it to the inaccessible areas detection is proposed.
and strengthen the crack detection more precisely by
acquiring images from it. Literature presents • Crack detection using image processing: Structure
morphological image processing technique to identify the The steps involved in image processing techniques are as
cracks. Research also focuses on the various image follows: (1) Acquisition of an image with the help of a camera
processing techniques used to detect crack. Based on the as a crack image as an input. (2) After acquisition the collected
review, analysis is done and a suitable conclusion is drawn. images go through pre-processing where it undergoes processes
This approach has helped in elevating our control over such as scaling and segmentation.(3)In colour image processing
manual inspection. ,some of the techniques are employed to process the deducted
image.(4) Finally, the feature extraction of image is done to
obtain the shape of the crack.
I. INTRODUCTION
Cracks are an important indicator when it comes to the safety
II. LITERATURE REVIEW
of an infrastructure. Effects such as cyclic loading, fatigue
This section provides an overview of all the image processing
stress develop internal stresses in the structure and leads to the
techniques and the algorithms used for the detection of cracks
development of cracks. In addition, effects like thermal
mostly in engineering structures.
expansion and contraction, human damage and surface changes
E. Balasubramanian et al. [1] have proposed a technique that
transcend material discontinuities which lead to failure. To
integrates Hat-transform and HSV thresholding for crack
prevent this damage a Crack detection process is employed.
detection. They have proposed an algorithm which combines
The crack detection can be done using two ways: (1) Manual
the output of the two filters resulting in enhancement of an
Inspection (2) Automated Inspection. In conventional methods,
output image. It was based on mathematical morphological
manual inspection was done by set of skilled inspectors with
approach and their study showed
the help of surveying instruments and visual examination to
that bottom hat transform was able to identify the cracks more
detect the irregularities and defects in the structure. However,
easily than the Top-hat transform. The former method was then
this method has certain drawbacks, as it is impossible for a
combined with the HSV thresholding which gave precise
crew to detect the cracks in inaccessible areas such as large
output of the cracks. In their methodology they used a novel
dams, monuments, buildings, etc. and also the estimation of
idea which uses an UAV (Unmanned aerial vehicle) for
size, length and width of the crack.
detecting the cracks in real time. They developed a GUI in
In order to get images of the structure in a required manner
Matlab that enabled them to detect and identify the cracks in
there is a need of a high resolution camera to get desired results
real time thereby saving the computational time.
through image processing. Because of its accuracy and
Shivaprasad K et al. [2] have proposed a simple technique to
simplicity in its results many of the image processing
detect cracks in pavements such as roads and concrete
techniques were proposed. Image processing techniques such
structures. They used normal edge detection algorithm as a
as Morphological approach, Hough transform, Edge detection
primary step as a pre-processing part to detect the false edges

IJERTV7IS030094 www.ijert.org 121

(This work is licensed under a Creative Commons Attribution 4.0 International License.)
 Published by : International Journal of Engineering Research & Technology (IJERT)
http://www.ijert.org ISSN: 2278-0181
Vol. 7 Issue 03, March-2018

of the crack. The false edges were removed by using obtained by using different types of classifiers. However, their
morphological approach. The drawback of the method was the experiments were subjected to eclectic cracks. These
obtained output images contained false edges which increased techniques were applicable for the cracks of split width greater
noise in the images. Proposed method was well suited for the than 0.3mm and object length greater than 15cm, which was
pre-dominant cracks. As an extension to their method they also the drawback of the project.
used thresholding technique ,and the obtained results were Arun Mohan, Sumathi Poobal [8] presented a review on the
good. analysis of types of imaging processing techniques used for
Anders Landster``om et al. [3] conducted experiments on steel crack detection. They surveyed several image processing
slabs for determination of cracks based on morphological techniques such as wavelet transform, median filtering, Hat
technique. The study focuses on 3D surface profile data transform. Morphological approach, Gabor filtering, Otsu’s
collected by laser triangulation based on morphological method, Statistical method, Superpixel algorithm, Data fusion
technique. Two sets of A and B of 3D profile were taken. filtering, Hough transform, Ultrasonic pulse velocity technique.
The data was processed in regions in the form of images of 150 Based on the analysis they focused their review on five features.
mm x 100 mm (width x length, or X x Y) in size. The Firstly, it was an objective based feature which consisted width
performance of the given method was verified by segmenting of the crack, length of the crack and direction of propagation of
and classifying a second independent validation set B, the crack.
containing 323 regions of 3D surface data collected from four Secondly, they analyzed the data sets used in the methods for
different steel slabs. The results obtained were satisfactory calculating real data and thereby making it more efficient.
leading to the collection of data nearly at 90% crack probability. Additionally, they presented the methods which provided high
The attractive result of their investigation was due to statistical accuracy. Finally, they performed the analysis of each image
classification and automated morphology method. processing techniques used in each system. Based on their
Gunkel et al.[4] have designed a crack detection algorithm .The analysis they concluded that the camera based image detection
micro cracks are detected using shortest possible path in crack with algorithms such as thresholding and morphological
clusters which also follows the darkest parts .They used technique proved to be efficient.
Dijkstra’s algorithm to detect the crack path which enabled in
analyzing kinks and curves of the crack. The method was III. ANALYSIS AND DISCUSSION
implemented in C and R programming language package which This section covers the analysis of the crack detection using
provided accurate results. image processing techniques based on the literature reviewed.
Kammar et al.[5] have proposed a system for road crack Based on the paper reviewed, it was observed that
detection and characterization to minimize the human Morphological approach was used in almost all the papers [1, 2,
involvement. In this type of imaging, they used Hough 3] and [7].The family of operations associated with
transformation for crack detection and supervised method for it(thickening , dilation, erosion, Hat-transform, opening and
the characterization of crack which is based on block-based closing) performed on on the shape of the subject of an image
image analysis approach. For each pixel the Hough transform is known as morphological approach. For robust results the
determines the straight line of that pixel and calculates the Hough Transform was used[5]. Due to its desirable features
slope of the line by mapping Cartesian coordinate into and real time inspection Hough transform are used for object
rotational coordinate system. Based on the obtained results the recognition. Moreover the statistical approach proved to be
cracks were classified and this two-step approach proved to be efficient and accurate for data analysis and filtering of
robust. images[5].For reduced computational time ,fuzzy logic [6] is
Pathak et al.[6] have presented a fuzzy logic approach for crack suitable method which predicted the cracks in nanoseconds.
detection which is an alternative for non-destructive test. They For easier segmentation of images in pre-processing stage
used natural frequency of the cracks in a beam as an input to techniques like HSV thresholding were adopted which
the fuzzy logic. The relative output obtained was the crack enhanced the quality of image making it more identifiable.
depth and relative position of the crack. Accordingly, the fuzzy Finally, analysis based on the image processing techniques
controller was prepared for varying natural frequencies. At the reviews the fact that the productivity of image processing
end, they [6] were able to predict the location of the crack and techniques were introduced only in the post-processing.
crack depth within nanoseconds which saved computational
time. IV. CONCLUSION
Zhang et.al[7] supervised the subway tunnel using This paper provides detailed survey of the image processing
Complementary Metal Oxide Semiconductor camera . techniques used to detect cracks in engineering structures. The
The captured images were stored in digital images. For main intention of the study was to review papers and analyse
extracting the data from the images they studied and the best technique that could be used for crack detection. Based
formulated an algorithm using morphological and thresholding on the paper reviewed we conclude that the image processing
technique. The extracted images were compared with grayscale techniques such as Morphological and Thresholding are the
images and they found that over 90% of crack length is most suitable for crack detection.The objectives such as
preserved in the last output image of binary images. width,depth,length and direction of propagation of crack can be
Additionally, the algorithm bottom hat transform proposed by analysed. The segmentation of images grouped into set of data
them helped them for the classification and crack detection give better and accurate results. An automated based UAV
purpose. The experimental results were based on different image processing proves to be efficient to detect the cracks in
parameter settings which showed that high accuracy can be real time thereby reducing human efforts and reaching

IJERTV7IS030094 www.ijert.org 122

(This work is licensed under a Creative Commons Attribution 4.0 International License.)
 Published by : International Journal of Engineering Research & Technology (IJERT)
http://www.ijert.org ISSN: 2278-0181
Vol. 7 Issue 03, March-2018

inaccessible areas easily. The literature encourages us to study

more on UAV’s and thermal infrared cameras which could help
to make the system efficient and error free.

REFRENCES
[1] S. Sankarasrinivasan, E. Balasubramanian, K. Karthika, U.
Chandrasekar and Rishi Gupta, Health Monitoring of Civil
Structures with Integrated UAV and Image Processing System,
Eleventh International Multi-Conference on Information
Processing-2015 (IMCIP-2015).
[2] Shivprasad .K,Vishwanath M K and Narasimha
Kaulgud,Morphology Based Surface Crack Detection,Journal of
Advanced and Science Volume I-2015.
[3] Anders Landstr¨om and Matthew J. Thurley, Morphology-Based
Crack Detection for Steel Slabs, IEEE Journal of Selected Topics
in Signal Processing, 2012.
[4] Christina Gunkel, Alexander Stepper, Arne C. Mu¨ller, Christine
H. Mu¨ ller, Micro crack detection with Dijkstra’s shortest path
algorithm, Mach. Vis. Appl. 23 (3) (2012).
[5] Vivekanandreddy, Navaneetha.D, Amruta Kammar,
Sowmyashree.B, Hough Transforms to Detect and Classify Road
cracks, International Journal of Engineering Research and
Technology (IJERT) Vol 3, June-2014.
[6] Patil Amit,Meghana Pathak,P.K.Sharma,Review of Numerical
Solution to the Detection of Crack in Structure by using Fuzzy
Logic,International Journal of Advance Research in Science And
Engineering,(IJARSE) Vol no.3,august-2014.
[7] Wenyu Zhang, Zhenjiang Zhang, Dapeng Qi and Yun Liu,
Automatic Crack Detection and Classification method for
Subway Tunnel Safety Monitoring, Sensors 2014 .
[8] Arun Mohan, Sumathi Poobal, Crack detection using image
processing: A critical review and analysis, Alexandria
Engineering Journal,2017.

IJERTV7IS030094 www.ijert.org 123

(This work is licensed under a Creative Commons Attribution 4.0 International License.)