IJCSI International Journal of Computer Science Issues, Vol.

7, Issue 3, No 1, May 2010 33

ISSN (Online): 1694-0784
ISSN (Print): 1694-0814

Towards Corrosion Detection System

B.B.Zaidan 1, A.A.Zaidan 2, Hamdan.O.Alanazi 3, Rami Alnaqeib 4

1
PhD Candidate / Department of Electrical and Computer Engineering/ Faculty of Engineering, / Multimedia University / 63100
Cyberjaya / Selangor Darul Ehsan, / Malaysia

2
PhD Candidate / Department of Electrical and Computer Engineering/ Faculty of Engineering, / Multimedia University / 63100
Cyberjaya / Selangor Darul Ehsan, / Malaysia

3
Master Student / Department of Computer System and Technology / Faculty of Computer Science and Information Technology /
University of Malaya / Kuala Lumpur/Malaysia

4
Master Student / Department of Information Technology / Faculty of Computer Science and Information Technology / University
of Malaya / Kuala Lumpur/Malaysia

Abstract coatings, so that aircraft primers and need not be stripped

[13]. Concrete and structural steel. Both materials decay in
Corrosion is a natural process that seeks to reduce the binding predictable ways, and bridges and over- passes made from
energy in metals. The end result of corrosion involves a metal them deteriorate to a level where the structures must be
atom being oxidized. Surface corrosion on aluminum aircraft
rehabilitated or replaced the cost of rehabilitating these
skins, near joints and around fasteners, is often an indicator of
buried structural corrosion and cracking In this paper we proposed
bridges or replacing them with new ones is staggering,
a new method on which we are moving towards designing a approximately $90 billion a year. Texture analysis is
method to detect the corrosion within the metals, the new method important in many applications of computer image analysis
has defined texture analysis as the main method for this approach, for classification [7], [8].
the proposed enhancement shows less false positive and less false In new simple methodology for the assessment of the
negative. The main functions used in this approach beside texture crown corrosion in concrete sewer pipes was developed
analysis are Edge detection, structure element and image dilation. based upon the principle that the surface roughness
The new approach has designed to detect a part of the image that increases when concrete corrodes [9]. The roughness was
has been affected by the corrosion, the tested images has showed a quantified by correlating the depths of the surface pits to
good result lying on detecting the corrosion part from the image.
the lengths of shadows produced in a single source of
incident light. A computer program was used to reconstruct
Keyword - Corrosion, Object Detection, Texture Analysis, Edge a pseudo three-dimensional concrete exterior and obtain the
Detection averaged corrosion rate [2]. In this paper that the use of
non-parametric classifiers based on learning algorithm
enables the proposed approach to be used in small robots
1. Introduction and portable devices for corrosion diagnosis. As the neural
network classifiers store the knowledge in the neurons
Corrosion is a physicochemical interaction between a metal weights, there is no need to store all data as in the
and its environment which results in changes in the parametric methods
properties of the metal and which may often lead to
impairment of the function of the metal, the environment
[12], [5], [4]. The corrosion resistance of metals and alloys 2. Why Texture Analysis
is a basic property related to the easiness with which these
materials react with a given environment. Today, aircraft Texture analysis methods have been utilized in a variety of
paints are routinely removed to reveal corrosion on metal application domains. In some of the mature domains (such
surfaces, and the aircraft must be repainted following as remote sensing) texture already has played a major role,
repairs. Both expensive and time-consuming, that process while in other disciplines (such as surface inspection) new
can also generate air pollution and waste resources. A applications of texture are being found [14].Texture
method is therefore needed to detect the early onset of analysis will play an important role in detecting this
corrosion on metal substrates covered by protective isolated data and reducing the error and improving the
IJCSI International Journal of Computer Science Issues, Vol. 7, Issue 3, No 1, May 2010 34
ISSN (Online): 1694-0784
ISSN (Print): 1694-0814

classification results [1]. Segmentation can be done by Edge detection methods utilize intensity gradients to detect
finding the pixels that lie on a region boundary. These the boundaries of objects [11].
pixels, called edges, can be found by looking at
neighbouring pixels. Since edge pixels are on the boundary
and regions on either side of the boundary may have
different gray values, a region boundary may be found by
measuring the difference between neighbouring pixels.
Most of edge detectors (local operators) use only intensity
characteristics as the basis for edge detection. Such
methods take advantage of gray level discontinuities that
are considered relevant features of the image [6].
And thus texture analysis with edge detection may use to
retrivel the objects that have a different texture Figure 1. Example of Canny Edge Detection.
characteristic from the image. In this paper we are moving
towerds implemnting an accurate method to detect the
corrosion, in fact, edge detection, texture analysis and other 4. Testing Result
factors has been embeded on this paper for the purpose of Below the output figures include a tables, these table has
tuning the system to have better result. five fields, sequentially, a, b, c, d and e, where (a) is the
original image, (b) is the gray level image, (c) is the texture
filter, (d) is the Edge detection, and finally (e) is the final
3. Methodology
enhanced image.
In this approach we will design and implement a method to Other test in figure 2 shows more complex corrosion, in
detect the corrosion within the metals, the new method will figure 2. The caption was for image that has two parts, one
define texture analysis as the main method for this part affected by corrosion and other part was not.
approach, texture analysis normally implement to segment The output shows a good accuracy of using the new
a special objects, however texture analysis can not stand approach to detect the corrosion on the image
alone without enhancing the images, whereby, the object
will be easy to detect. The main assistance functions will be
edge detection, create structure elements and finally dilate a
the edge of the structured objects. The expected result will
be a system can detect the corrosion.. This texture filter has
been invented originally to calculate the local range of an
image. These statistics can characterize the texture of an
image because they provide information about the local
variability of the intensity values of pixels in an image. For
example, in areas with smooth texture, the range of values
in the neighborhood around a pixel will be a small value; in
areas of rough texture, the range will be larger, The stdfilt
and entropyfilt functions operate similarly, defining a
neighborhood around the pixel of interest and calculating
the statistic for the neighborhood to determine the pixel
value in the output image. The stdfilt function calculates
the standard deviation of all the values in the neighborhood. b
The entropyfilt function calculates the entropy of the
neighborhood and assigns that value to the output pixel.
Note that, by default, the entropyfilt function defines a 9-
by-9 neighborhood around the pixel of interest. To
calculate the entropy of an entire image, use the entropy
function.
Edge detection is the process of finding sharp contrasts in
intensities in an image [10]. This process significantly
reduces the amount of data in the image, while preserving
the most important structural features of that image. Canny
edge detection operator was developed by John F. Canny in
1986 and uses a multi-stage algorithm to detect a wide
range of edges in images, Edge detection methods such as
the canny detector [3] were widely applied for this task.
IJCSI International Journal of Computer Science Issues, Vol. 7, Issue 3, No 1, May 2010 35
ISSN (Online): 1694-0784
ISSN (Print): 1694-0814

c characteristics in the image processing; in this paper texture

analysis through stdfilt filter has been proposed to detect
the corrosion within the plates. The proposed solution has
focused on the rough texture of the corrosion areas, and
identifies the simple texture as non-corrosion area. The test
has shows a good result in term of detecting visible
corrosion, as well, we assumed the new approach may do
the job successfully with the under-paint corrosion.

ACKNOWLEDGEMENT

Thanks in advance for the entire worker in this project, and

the people who support in any way, also I want to thank
e MMU for the support which came from them.

REFERENCES

[1] Alhaddad, B. I. Z., M. C. Burns, et al. (2007). Texture

Analysis for Correcting and Detecting Classification
Structures in Urban Land Uses. Urban Remote Sensing
Joint Event. Spain.
[2] Bento, M. P., F. N. S. de Medeiros, et al. (2009).
Image Processing Techniques applied for Corrosion
Damage Analysis.
[3] Canny, J. (1987). "A computational approach to edge
f detection." Readings in computer vision: issues,
problems, principles, and paradigms: 184.
[4] Demadis, K. D. (2007).,"ALKALINE EARTH
METAL PHOSPHONATES: FROM SYNTHETIC
CURIOSITIES TO N ANOTECHNOLOG Y
APPLICATIONS." Solid State Chemistry Research
Trends: 109.
[5] Demadis, K. D., C. Mantzaridis, et al. (2006). "Effects
of Structural Differences on Metallic Corrosion
Inhibition by Metal- Polyphosphonate Thin Films."
Ind. Eng. Chem. Res 45(23): 7795-7800.
[6] Di Ruberto, C., G. Rodriguez, et al. (1999). Image
segmentation by texture analysis.
[7] Dunker, K. F. and B. G. Rabbatt (1993). "Why
Figure 2. Other Corrosion Detect by the System America's bridges are crumbling." Scientific American
268(3): 18-24.
[8] Ehlen, M. A. (1997). "Life-cycle costs of new
5. Conclusions construction materials." Journal of Infrastructure
Systems 3(4): 129-133.
Texture segmentation is a significant and primary issue in
texture analysis. It is concerned with automatically [9] Gutierrez-Padilla, M., D. Guadalupe, et al. (2009).
determining the boundaries between various textured "Simple scanner-based image analysis for corrosion
regions in an image detection approaches has been widely testing: Concrete application." Journal of Materials
used in the image processing. It has represented less time Processing Technology 209(1): 51-57.
consuming and inexpensive alternative. Many techniques [10] Hamid, A. M., M. L. M. Kiah, et al. (2009). "Novel
and functions were involve on the image processing to Approach for High Secure and High Rate Data Hidden
achieve an accurate methods on detect, recognize and in the Image Using Image Texture Analysis."
classify the target, the most popular methods on these area International Journal of Engineering and Technology
are, texture analysis, image segmentation and many other (IJET): 0975-4042.
functions. Texture analysis is one of the most important
IJCSI International Journal of Computer Science Issues, Vol. 7, Issue 3, No 1, May 2010 36
ISSN (Online): 1694-0784
ISSN (Print): 1694-0814

[11] Haralick, R. M. (1979). "Statistical and structural Hamdan Al-Anazi: He has obtained
approaches to texture." Proceedings of the IEEE 67(5): his bachelor degree from “King Saud
786-804. University”, Riyadh, Saudi Arabia. He
worked as a lecturer at Health
[12] Javaherdashti, R. (2000). "How corrosion affects College in the Ministry of Health in
industry and life." Anti-Corrosion Methods and Saudi Arabia, and then he worked as
Materials 47(1): 30-34. a lecturer at King Saud University in
[13] Lipkin, B. S. and A. Rosenfeld (1970). Picture the computer department. Currently
processing and psychopictorics, Academic Press, Inc. he is Master candidate at faculty of Computer Science &
Information Technology at University of Malaya in Kuala
Orlando, FL, USA.
Lumpur, Malaysia. His research interest on Information
[14] Tuceryan, M. and A. K. Jain (1993). "Texture Security, cryptography, steganography, Medical
analysis." Handbook of pattern recognition and Applications, and digital watermarking, He has contributed
computer vision 276. to many papers some of them still under reviewer.
 
Rami Alnaqeib - he is master student in the Department of
Bilal Bahaa Zaidan: He obtained his Information Technology / Faculty of Computer Science and
bachelor degree in Mathematics and Information Technology/University of Malaya / Kuala
Computer Application from Saddam Lumpur/Malaysia, He has contribution for many papers at
University/Baghdad followed by international conferences and journals.
master in data communication and
computer network from University of
Malaya. He led or member for many
funded research projects and He has
published more than 60 papers at
various international and national
conferences and journals, His interest area are Information
security (Steganography and Digital watermarking), Network
Security (Encryption Methods) , Image Processing (Skin
Detector), Pattern Recognition , Machine Learning (Neural
Network, Fuzzy Logic and Bayesian) Methods and Text
Mining and Video Mining. .Currently, he is PhD Candidate
on the Department of Electrical & Computer Engineering /
Faculty of Engineering / Multimedia University / Cyberjaya,
Malaysia. He is members IAENG, CSTA, WASET, and
IACSIT. He is reviewer in the (IJSIS, IJCSN, IJCSE and
IJCIIS).

Aos Alaa Zaidan: He obtained his

1st Class Bachelor degree in
Computer Engineering from
university of Technology / Baghdad
followed by master in data
communication and computer
network from University of Malaya.
He led or member for many funded
research projects and He has
published more than 60 papers at
various international and national
conferences and journals, His interest area are Information
security (Steganography and Digital watermarking), Network
Security (Encryption Methods) , Image Processing (Skin
Detector), Pattern Recognition , Machine Learning (Neural
Network, Fuzzy Logic and Bayesian) Methods and Text
Mining and Video Mining. .Currently, he is PhD Candidate
on the Department of Electrical & Computer Engineering /
Faculty of Engineering / Multimedia University / Cyberjaya,
Malaysia. He is members IAENG, CSTA, WASET, and
IACSIT. He is reviewer in the (IJSIS, IJCSN, IJCSE and
IJCIIS).