Pipeline Crack Detection Using Mathematical Morphological Operator

  • A. Prema Kirubakaran
  • I. V. Murali Krishna


A pipeline crack is a major hazard to any type of liquid transportation. Oil industry depends mainly on human detection of these cracks, which leads to many problems from health to environment disaster. To detect a crack, pipelines’ inner layers are X-rayed, and these X-rays were later manually evaluated for cracks and holes. This technique evolves lot of time and resources. This proposed research work helps to diminish this problem by analyzing the cracks and holes through a computerized solution. A pipeline with crack is analyzed using image analysis and processing which comprises of various pattern recognition techniques. Image analysis and processing is one of the most powerful innovations in today’s world. It brings all kinds of pattern recognition together and solves the problem of data identification and misuse of data. This is achieved by applying the method of pattern analysis and recognition. As a result, this technique of image analysis and processing is used to detect the holes and cracks which occur in a pipeline that carries any type of liquids and gases. This paradigm helps in environmental safety. As in the pipeline industry there are many man-made equipments and methods, computer application to carry out these process is lacking. To make a shift over to the computerized image recognition, high-frequency filter (HFF) with Gate Turn off thyristor (GTO) using unsupervised-based learning algorithm is implemented. Mathematical morphological operator and edge detection principles are used for image evaluation. Initially a digital camera with fiber optic cable is passed inside a pipeline to capture the cracked images. These images are converted as raster images and stored as bits. Later, these images are processed to view for hidden points using unsupervised cluster algorithm; after evaluating the hidden points, the crack has to be measured for its length and to identify the location where it occurs and this is achieved by developing mathematical morphological operator. Images are always not clear, so the dataset formed is always unclear; in order to smooth the images, the edge detection principle is applied. The captured images are read as pixel groups, after converting into raster images. If the pixels grouped as clusters are clear with no zero bit values, it denotes that the pipeline is without any crack else even a small relapse in any one of the pixel will make the image vague. The blurred picture denotes that there is a defect in the pipeline. This helps to locate the image with defect, which is rectified and thus it results in an effective, defect-free passage that will carry any type of liquid or gas. The extraction of hidden patterns from a large quantity of data recognition activities seems to be a major conflict in image detection. Usually, the size of a pipeline is 22 m; in order to avoid the problem of large data, the length to capture an image can be reduced to 10 m and later the rest. The safety of the environment and the manual operator is very important during the transportation of any substance in a pipeline; this major security concern has made image detection to become a popular component in the area of image analysis and processing. In traditional manual detection systems, the manual operator needs to spend much time in analyzing the data and also it generates high false data rates. There is an urgent need for effective and efficient methods to discover both the unknown and unexpected novel image display over a pipeline network from those that are extremely large in size and high in dimensionality and complexity. So the pattern recognition-based image analysis detection systems have been chosen which are more precise and require less manual processing time and input from human experts. This research focuses on solving the issues in image detection communities that can help the system operator to make processing, classification, labeling of data and to mitigate the outcome of image data. The system administrator finds it difficult to preprocess the data. Even though it has been done successfully, the overwhelming output of the images makes the task a failure and even sometimes images go unidentified. To overcome this situation, frequent updating of data is needed. In order to reduce the workload of the administrator, four major image analysis and processing techniques involving pattern recognition task have been introduced. Image detection datasets have been used in this research, and the proposed algorithms will be implemented in MATLAB. In this research, for classification of network data, several existing algorithms like Kohonen-cluster algorithm, Canny’s edge detection algorithm, and mathematical morphological operator algorithm for the simulation of images are proposed. The crack is measured using mathematical morphological operator. Mathematical morphology is evaluated using the concept of geometric measurements. Set theory is applied to evaluate morphological-based geometric measurements. An important technical goal is to provide sufficient information so that the readers can apprehend and possibly implement the technique that has been derived. The result of this study will build a system, for identifying the defects in an oil pipe, by matching to an image database. This system can be implemented or replaced with the existing manual one. Need of this topic: Engineers pursuing mechanical stream and who would like to have a career from normal mechanical to oil pipeline can refer the topic through this book for their career enhancement. The chapters on erosion, corrosion, and dilation will help them to make a more effective study on cracks and holes which can be applied through robotics. This book will focus more on detecting the cluster cracks that are neglected during an inspection of an oil pipeline. This concept of detecting a hole or a crack can be applied to any type of pipeline that is going to transport any type of substances. The topic of the book can be the same or it can be altered according to the needed definition of the engineering society. The opportunity to write these chapters will help to learn more about the mathematical operators to detect a clustered crack.


  1. 1.
    Aldenderfer, M. S., & Blashfield, R. K. (1988). Sage university paper on quantitative applications in social science. Cluster Analysis, 36(1), 1–13.Google Scholar
  2. 2.
    Wardhani, A. W., & Gonzalez, R. (1998). Automatic image structure analysis. e-prints (pp. 1–9). Google Scholar
  3. 3.
    Ledda, A., & Luong, H. Q. (2006). Image interpolation using mathematical morphology (pp. 12–49).Google Scholar
  4. 4.
    Bhoite, A. (2011) Automated fiber optic cable end face field inspection. Technologic, 3–8.Google Scholar
  5. 5.
    Blashfield, R. K., & Aldenderfer, M. S. (1978). The literature on cluster analysis. Multivariate Behavioral Research, 13, 271–295.CrossRefGoogle Scholar
  6. 6.
    Busch, C., & Eberle, M. (1995). Morphological operations for color-coded images. In F. Post & M. Göbel (Eds.), Proceedings of the European Association for Computer Graphics (pp. 193–204).Google Scholar
  7. 7.
    Can, F., & Ozkarahan, E. A. (1984). Two partitioning type clustering algorithms. Journal of the Association for Information Science and Technology, 35, 268–276.Google Scholar
  8. 8.
    Can, F., & Ozkarahan, E. A. (1989). Dynamic cluster maintenance. Information Processing and Management, 25, 275–291.CrossRefGoogle Scholar
  9. 9.
    Canny, J. (1986). A computational approach to edge detection (pp. 3–6).Google Scholar
  10. 10.
    Crouch, C. J. (1988). A cluster-based approach to thesaurus construction. In 11th International Conference on Research and Development in Information Retrieval (pp. 309–320). New York.Google Scholar
  11. 11.
    Domingo, J., Benavent, X., Vegara, F., & Pelechano, J. (2005). A new approach for image colour morphology (pp. 234–245). Tech. Rep., Institute of Robotics, University of Valencia.Google Scholar
  12. 12.
    Dougherty, E. R., & Astola, J. (1994). Introduction to non-linear image processing. Bellingham, Washington: Spie.Google Scholar
  13. 13.
    El-Hamdouchi, A. (1987). The use of inter-document relationships in information retrieval. Ph.D. thesis, University of Sherfield.Google Scholar
  14. 14.
    Ester, M., Kriegel, H.-P., & Sander, J. (1996). A density based algorithm for discovering clusters in large spatial database with noise (pp. 226–231).Google Scholar
  15. 15.
    Everitt, B. (1980). Cluster analysis. In F. Khalvati (Ed.), Computational redundancy in image processing (pp. 4–6, 3–57, 2nd ed.).Google Scholar
  16. 16.
    Gonzalez, P., Cabezas, V., Mora, M., Cordova, F., & Vidal, J. (2010). Morphological color images processing using distance-based and lexicographic order operators. In Proceedings of the 29th International Conference of the Chilean Computer Science Society.Google Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2018

Authors and Affiliations

  1. 1.Department of Computer ScienceAnnai Violet Arts & Science CollegeChennaiIndia
  2. 2.IIT MadrasChennaiIndia
  3. 3.Remote SensingNRSA, ISROHyderabadIndia

Personalised recommendations