Advertisement

Toward Developing an Enhanced Hough Transform Technique for Circle and Semicircle Detection

  • Ismariani IsmailEmail author
  • Adeline Engkamat
  • Abang Feizal Abang Ibrahim
Conference paper

Abstract

Image segmentation is one of the techniques to localize shapes in an image. There are three components of image segmentation which are; image thresholding, edge-based segmentation, and region-based segmentation. In this research, we focused only on one of edge-based segmentation technique which is Hough transform, that can detect circular shapes in an image. However, it was found that there are problems with the existing Hough transform where it is unable to detect a circular shape with unknown radius and it is also unable to detect semicircular shapes. Thus, in this research, Hough transform is enhanced to solve these problems by comparing the pattern of graphs and by looking at the Hough peaks in the Hough transform matrix. In the testing part, results for both semicircle and circle images underwent the process of measuring the quantity of accepted and rejected images using confusion matrix. The results revealed that the accuracy of circle and semicircle detection in modified Hough transform has better performance compared to the existing Hough transform. Thus, this new enhanced technique could be used in the development of a methodology that will be of value in future studies of circle detection in image segmentation; such as in medical area to locate tumors and other pathologies, to locate objects in satellite images, iris recognition, and face recognition.

Keywords

Circle detection Hough transform Image segmentation Semicircle detection Shape detection 

References

  1. Chia AYS, Leung MKH, Eng H-L, Rahardja S (2007) Ellipse detection with Hough transform in one dimensional parametric space. In: Conference: IEEE international conference on image processing, 2007 (ICIP 2007), 333–336Google Scholar
  2. Guo S, Zhang X, Zhang F (2006) Adaptive randomized Hough transform for circle detection using moving window. In: Proceedings of the fifth international conference on machine learning and cybernetics, 13–16 Aug, IEEE, Dalian, pp 3880–3885Google Scholar
  3. Kubat M, Holte R, Matwin S (1998) Machine learning for the detection of oil spills in satellite radar images. Mach Learn 30, 195–215Google Scholar
  4. Kohavi R, Provost F (1998) On applied research in machine learning. In: Editorial for the Special Issue on Applications of Machine Learning and the Knowledge Discovery Process, vol 30. Columbia University, New York, pp 1–6Google Scholar
  5. Rabindra KM, Meena J (2009) Image segmentation using Hough transform. Bachelor, National Institute of Technology, RourkelaGoogle Scholar
  6. Seul M, O’Gorman L, Sammon MJ (2000) Practical algorithm for image analysis description, examples and code. Cambridge University Press, Cambridge, UKGoogle Scholar
  7. Shapiro LG, Stockman GC (2001) Computer vision. Prentice-Hall, Inc, USAGoogle Scholar
  8. Shuai Z, Ze Z, Hai-Tao W (2010) Research of robot color logo orientation based on Hough transform. In: 2010 second international conference on intelligent human-machine systems and cybernetics. IEEE, pp 56–60Google Scholar
  9. Sirisak L, Boonruang M, Ratchadaporn O, Anant O (2011) Extracted circle Hough transform and circle defect detection algorithm. World Academy of Science, Engineering and Technology, International Science Index 12Google Scholar
  10. Tcl (2005) Object detection using Hough transform. Retrieved from http://basiceng.blogspot.com/2005/12/object-detection-using-hough-transform.html
  11. Thuy TN, Xuan DP, Jae WJ (2008) An improvement of the standard Hough transform to detect line segments. In: Proceedings IEEEGoogle Scholar
  12. Yue GH, Lu CH, Sheng LQ, Liu YN (2012) A combined method for concentric circles detection in image of o-shape rubber ring. Adv Mat Res 488–489:1619–1623 (Trans Tech Publications, Switzerland)Google Scholar
  13. Zapata J, Vilar R, Ruiz R (2011) Automatic inspection system of welding radiographic images based on ANN under a regularisation process. Springer Science + Business Media, LLC 2011Google Scholar

Copyright information

© Springer Science+Business Media Singapore 2016

Authors and Affiliations

  • Ismariani Ismail
    • 1
    Email author
  • Adeline Engkamat
    • 1
  • Abang Feizal Abang Ibrahim
    • 2
  1. 1.Faculty of Computer and Mathematical SciencesUniversiti Teknologi MARAKota SamarahanMalaysia
  2. 2.Faculty of Business ManagementUniversiti Teknologi MARAKota SamarahanMalaysia

Personalised recommendations