Advertisement

Feature extraction from multi-directional multi-resolution image transformations for the classification of zoom-endoscopy images

  • Michael Häfner
  • Roland KwittEmail author
  • Andreas Uhl
  • Alfred Gangl
  • Friedrich Wrba
  • Andreas Vécsei
Theoretical Advances

Abstract

In this article, we discuss the discriminative power of a set of image features, extracted from detail subbands of the Gabor wavelet transform and the dual-tree complex wavelet transform for the purpose of computer-assisted zoom-endoscopy image classification. We incorporate color channel information into the classification process and show that this leads to superior classification results, compared to luminance-channel-only-based image analysis.

Keywords

Zoom-endoscopy Wavelet transform Classification Texture analysis 

Notes

Acknowledgments

This work is funded by the Austrian Science Fund (FWF) under Project No. L366-N15.

References

  1. 1.
    Fukunaga K (1990) Introduction to statistical pattern recognition. Morgan Kaufmann, Menlo ParkGoogle Scholar
  2. 2.
    Häfner M, Brunauer L, Payer H, Resch R, Wrba F, Gangl A, Vécsei A, Uhl A (2007) Pit pattern classification of zoom-endoscopic colon images using DCT and FFT. In: Kokol P, Podgorelec V, Micetic-Turk D, Zorman M, Verlic M (eds) Proceedings of the 20th IEEE International Symposium on Computer-Based Medical Systems (CBMS 2007), Maribor, June 2007. IEEE Computer Society CPS, New York, pp 159–164Google Scholar
  3. 3.
    Häfner M, Brunauer L, Payer H, Resch R, Wrba F, Gangl A, Vécsei A, Uhl A (2007) Pit pattern classification of zoom-endoscopical colon images using evolved Fourier feature vectors. In: Diamantaras K, Adali T, Pitas I, Larsen J, Papadimitriou T, Douglas S (eds) Proceedings of the 2007 IEEE Machine Learning for Signal Processing Workshop (MLSP’07), Thessaloniki, August 2007. IEEE, New York, pp 99–104Google Scholar
  4. 4.
    Häfner M, Kendlbacher C, Mann W, Taferl W, Wrba F, Gangl A, Vecsei A, Uhl A (2006) Pit pattern classification of zoom-endoscopic colon images using histogram techniques. In: Proceedings of the 7th Nordic Signal Processing Symposium (NORSIG’06), pp 58–61, ReykjavikGoogle Scholar
  5. 5.
    Häfner M, Liedlgruber M, Wrba F, Gangl A, Vecsei A, Uhl A (2006) Pit pattern classification of zoom-endoscopic colon images using wavelet texture features. In: Proceedings of the 3rd International Conference on Advances in Medical Signal and Image Processing (MEDSIP’06), GlasgowGoogle Scholar
  6. 6.
    Haralick RM (1973) Textural features for image classification. IEEE Trans Syst Men Cybern 3(6):610–621CrossRefMathSciNetGoogle Scholar
  7. 7.
    Hatipoglu S, Mitra N, Kingsbury S (1999) Texture classification using dual-tree complex wavelet transform. In: Proceedings of the 7th International Conference on Image Processing and Its Applications, pp 344–347, BrisbaneGoogle Scholar
  8. 8.
    Hurlstone DP (2002) High-resolution magnification chromoendoscopy: common problems encountered in pit-pattern interpretation and correct classification of flat colorectal lesions. Am J Gastroenterol 97(4):1069–1070Google Scholar
  9. 9.
    Karkanis SA, Iakovids DK, Maroulis DE (2003) Computer-aided tumor detection in endoscopic video using color wavelet features. IEEE Trans Inform Technol Biomed 7(3):141–152CrossRefGoogle Scholar
  10. 10.
    Kingsbury N (1998) The dual-tree complex wavelet transform: a new technique for shift-invariance and directional filters. In: Proceedings of the 8th IEEE DSP Workshop, pp 9–12, Bryce Canyon, UtahGoogle Scholar
  11. 11.
    Kingsbury N (2001) Complex wavelets for shift-invariant analysis and filtering of signals. J Appl Comput Harmonic Anal 10(3):234–253zbMATHCrossRefMathSciNetGoogle Scholar
  12. 12.
    Kittler J, Hatef M, Duin RPW, and Matas J (1998) On combining classifiers. IEEE Trans Pattern Anal Mach Intell 20(3):226–239CrossRefGoogle Scholar
  13. 13.
    Kudo S (1994) Colorectal tumours and pit pattern. J Clin Pathol 47:880–885CrossRefGoogle Scholar
  14. 14.
    Kudo S, Tamura S, Nakajima T, Yamano H, Kusaka H, Watanabe H (1996) Diagnosis of colorectal tumorous lesions by magnifying endoscopy. Gastrointest Endosc 44(1):8–14CrossRefGoogle Scholar
  15. 15.
    Kwitt R, Uhl A (2007) Modeling the marginal distributions of complex wavelet coefficient magnitudes for the classification of zoom-endoscopy images. In: Proceedings of the IEEE Computer Society Workshop on Mathematical Methods in Biomedical Image Analysis (MMBIA’07), Rio de JaneiroGoogle Scholar
  16. 16.
    Manjunath BS and Ma WY (1996) Texture features for browsing and retrieval of image data. IEEE Trans Pattern Anal Mach Intell 18(8):837–842CrossRefGoogle Scholar
  17. 17.
    Meining A (2004) Inter- and intra-observer variability of magnification chromoendoscopy for detecting specialized intestinal metaplasia at the gastroesophageal junction. Endoscopy 36(2):160–164CrossRefGoogle Scholar
  18. 18.
    Palm C (2004) Color texture classification by integrative cooccurrence matrices. Pattern Recognit 37(5):965–976CrossRefGoogle Scholar
  19. 19.
    Saito N, Coifman R (1994) Local discriminant bases. Math Imaging Wavelet Appl Signal Image Process II 2303:2–14Google Scholar
  20. 20.
    Selesnick I, Baraniuk R, and Kingsbury N (2005) The dual-tree complex wavelet transform. IEEE Signal Process Mag 22(6):123–151CrossRefGoogle Scholar
  21. 21.
    Van de Wouwer G, Livens S, Scheunders P, Van Dyck D (1997) Color texture classification by wavelet energy correlation signatures. In: Proceedings of the 9th International Conference on Image Analysis and Processing (ICIAP’97). Springer, Berlin, pp 327–334Google Scholar
  22. 22.
    Zuiderveld K (2004) Contrast limited adaptive histogram equalization, Chap. VIII.5, pp 474–485. Graphics GEMS IV. Morgan Kaufmann, Menlo ParkGoogle Scholar

Copyright information

© Springer-Verlag London Limited 2008

Authors and Affiliations

  • Michael Häfner
    • 1
  • Roland Kwitt
    • 2
    Email author
  • Andreas Uhl
    • 2
  • Alfred Gangl
    • 1
  • Friedrich Wrba
    • 3
  • Andreas Vécsei
    • 4
  1. 1.Department of Clinical PathologyVienna Medical UniversityViennaAustria
  2. 2.Department of Computer SciencesUniversity of SalzburgSalzburgAustria
  3. 3.Department of Gastroenterology and HepatologyVienna Medical UniversityViennaAustria
  4. 4.St. Anna Children’s HospitalViennaAustria

Personalised recommendations