Modified Kittler and Illingworth’s Thresholding for MRI Brain Image Segmentation

  • T. Kalaiselvi
  • P. Nagaraja
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8284)

Abstract

This work is aimed to produce a robust thresholding method for segmenting the MRI brain images. A popular thresholding method commonly used in digital image segmentation is the Kittler and Illingworth’s (MET) method because it improves the segmentation process effectively. It is easy to implement and works well with the general images. However, it fails to segment the MRI brain images. This paper proposed a method to modify the objective function of traditional MET method by including the total variance of given image and a weight parameter. This method gives the satisfactory results for the MRI brain images, while compared with other threshold methods and traditional MET method. The segmented images are compared by using the region non–uniformity (NU) parameter. The NU value of proposed work is very low while compared with the original and other existing methods. The MRI brain images are segmented by the proposed work have sub structural clarity for further processing.

Keywords

Image Segmentation Kittler and Illingworth MRI brain Images Thresholding 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Gonzalez, R.C., Woods, R.E.: Digital Image Processing. Pearson Education, Inc. Publication, New Delhi (2009)Google Scholar
  2. 2.
    Sonka, M., Hlavac, V., Boyal, R.: Digital Image Processing and Computer Vision. Cengage Learning (2008)Google Scholar
  3. 3.
    Kalaiselvi, T.: Brain Portion Extraction and Brain Abnormality Detection from Magnet Resonance Imaging of Human Head Scans. Pallavi Publications, Tamil Nadu (2011)Google Scholar
  4. 4.
    Al-amri, S.S., Kalyankar, N.V., Khamitkar, S.D.: Image Segmentation using Threshold Techniques. Journal of Computing 2 (2010)Google Scholar
  5. 5.
    Xue, J.H., Zhang, Y.J.: Ridler and Calvards, Kittler and Illingworths and Otsus Methods for Image Thresholding. Pattern Recognition Letters 33, 793–797 (2012)CrossRefMathSciNetGoogle Scholar
  6. 6.
    Sahoo, P.K., Soltani, S., Wong, A.K.C.: Survey of Thresholding Techniques, Computer Vision. Graphics and Image Processing 41, 230–260 (1988)Google Scholar
  7. 7.
    Sauvola, J., Pietikainen, M.: Adaptive Document Image Binarization. Pattern Recognition 33(2), 225–236 (2000)CrossRefGoogle Scholar
  8. 8.
    Otsu, N.: A Threshold Selection from Gray level Histograms. IEEE Transactions of systems, Man and Cybernetics (SMC) 9(1), 62–66 (1979)CrossRefMathSciNetGoogle Scholar
  9. 9.
    Shaikh, S.H., Maiti, A.K., Chaki, N.: A New Image Binarization Method using Iterative Partitioning. Springer- Machine Vision and Applications (2012)Google Scholar
  10. 10.
    Nikolaos, N., Dimitris, V.: A binarization algorithm for historical manuscripts. In: 12th WSEAS International Conference on Communications, Heraklion, Greece, July 23–25, pp. 41–51 (2008)Google Scholar
  11. 11.
    Kalaiselvi, T., Nagaraja, P.: A Robust Thresholding Technique for Image Segmentation from General Gray Images. In: Proceedings of ICAMTCS–2013, pp. 183–188 (January 2013)Google Scholar
  12. 12.
    Sezgin, M., Sankur, B.: Survey Over Image thresholding Techniques and Quantitative Performance Evaluation. Journal of Electronic Imaging 13(1), 146–165 (2004)CrossRefGoogle Scholar
  13. 13.
    Kittler, J., Illingworth, J.: Minimum Error Thresholding. Pattern Recognition 19, 41–47 (1986)CrossRefGoogle Scholar
  14. 14.
    The Whole Brain Atlas (WBA), Department of Radiology and Neurology at Brigham and Womens Hospital, Harvard Medical School, Boston, USAGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2013

Authors and Affiliations

  • T. Kalaiselvi
    • 1
  • P. Nagaraja
    • 1
  1. 1.Image Processing Lab, Department of Computer Science and ApplicationsGandhigram Rural Institute-Deemed UniversityDindigulIndia

Personalised recommendations