Medical & Biological Engineering & Computing

, Volume 45, Issue 12, pp 1211–1222

Shift-invariant discrete wavelet transform analysis for retinal image classification

Original Article


This work involves retinal image classification and a novel analysis system was developed. From the compressed domain, the proposed scheme extracts textural features from wavelet coefficients, which describe the relative homogeneity of localized areas of the retinal images. Since the discrete wavelet transform (DWT) is shift-variant, a shift-invariant DWT was explored to ensure that a robust feature set was extracted. To combat the small database size, linear discriminant analysis classification was used with the leave one out method. 38 normal and 48 abnormal (exudates, large drusens, fine drusens, choroidal neovascularization, central vein and artery occlusion, histoplasmosis, arteriosclerotic retinopathy, hemi-central retinal vein occlusion and more) were used and a specificity of 79% and sensitivity of 85.4% were achieved (the average classification rate is 82.2%). The success of the system can be accounted to the highly robust feature set which included translation, scale and semi-rotational, features. Additionally, this technique is database independent since the features were specifically tuned to the pathologies of the human eye.


Retinal images Shift-invariant DWT Feature extraction 


  1. 1.
    Aksoy S, Haralick R (1998) Textural features for image database retrieval. In: Proceedings of IEEE workshop on content-based access of image and video libraries, pp 45–49Google Scholar
  2. 2.
    Armstrong A, Jiang J (2001) An efficient image indexing algorithm in JPEG compressed domain. In: International conference on image processing, pp 350–351Google Scholar
  3. 3.
    Balakrishnama S, Ganapathiraju A, Picone J (1999) Linear discriminant analysis for signal processing problems. In: Proceedings of IEEE Southeastcon, pp 78–81Google Scholar
  4. 4.
    Barrett S, Rylander HG, III AW (1994) Automated lesion data base building for the treatment of retinal disorders. In: Proceedings IEEE international conference image processing, pp 426–430Google Scholar
  5. 5.
    Beylkin G (1992) On the representation of operators in bases of compactly supported wavelets. SIAM J Numer Anal 29:1716–1740MATHCrossRefMathSciNetGoogle Scholar
  6. 6.
    Bradley A (2003) Shift-invariance in the discrete wavelet transform. Digital image computing: techniques and applications, pp 29–38Google Scholar
  7. 7.
    Braga-Neto U, Dougherty E (2004) Is cross-validation valid for small-sample microarray classification? Bioinformatics 20(3):374–380CrossRefGoogle Scholar
  8. 8.
    Brandon L, Hoover A (2003) Drusen detection in a retinal image using multi-level analysis. MICCAI 618–625Google Scholar
  9. 9.
    Burrus C, Gopinath R, Guo H (1998) Introduction to wavelets and wavelet transforms: a primer. Prentice Hall International, HoustonGoogle Scholar
  10. 10.
    Chang S (1995) Compressed-domain techniques for image/video indexing and manipulation. In: International conference on image processing, pp 314–317Google Scholar
  11. 11.
    Chiu C, Wong H, Ip HS (2004) Compressed domain feature transformation using evolutionary strategies for image classification. In: International conference on image processing, pp 429–432Google Scholar
  12. 12.
    Cohen I, Raz S, Malah D (1997) Orthonormal shift-invariant wavelet packet decomposition and representation. Signal Process 57:251–270MATHCrossRefGoogle Scholar
  13. 13.
    Coifman R, Saito N (1995) Local discriminant bases and their applications. J Math Imaging Vis 5:337–358MATHCrossRefMathSciNetGoogle Scholar
  14. 14.
    Coifman R, Wickerhauser M (1992) Entropy-based algorithms for best basis selection. IEEE Trans Inf Theory 38:713–718MATHCrossRefGoogle Scholar
  15. 15.
    Falzon F, Mallat S (1998) Analysis of low bit rate image transform coding. IEEE Trans Signal Process 46(4):1027–1042CrossRefGoogle Scholar
  16. 16.
    Foracchia M, Grisan E, Ruggeri A (2004) Detection of optic disc in retinal images by means of a geometrical model of vessel structure. IEEE Trans Med Imaging 23(10):1189–1195CrossRefGoogle Scholar
  17. 17.
    Fukunaga K, Hayes R (1989) Effects of sample size in classifier design. IEEE Trans Pattern Anal Mach Intell 11(8):873–885CrossRefGoogle Scholar
  18. 18.
    Goldbaum M (2002) STARE: structured analysis of the Retina. World Wide Web.
  19. 19.
    Haralick R, Shanmugam K, Dinstein I (1973) Textural features for image classification. IEEE Trans Syst Man Cybern 3(6):610–621CrossRefGoogle Scholar
  20. 20.
    Julesz B (1981) Textons, the elements of texture perception, and their interactions. Nature 290(5802):91–97CrossRefGoogle Scholar
  21. 21.
    Khademi A (2006) Multiresolutional analysis for classification and compression of medical images. Master’s thesis. Ryerson University, CanadaGoogle Scholar
  22. 22.
    Leung M, Peterson A (1992) Scale and rotation invariant texture classification. In: Conference record of the twenty-sixth asilomar conference on signals, systems and computers, pp 461–465Google Scholar
  23. 23.
    Liang J, Parks T (1994) A two-dimensional translation invariant wavelet representation and its applications. In: IEEE international conference on image processing, pp 66–70Google Scholar
  24. 24.
    Liang J, Parks T (1996) Translation invariant wavelet transforms with symmetric extensions. In: IEEE digital signal processing workshop, pp 69–72Google Scholar
  25. 25.
    Liang J, Parks T (1996) A translation-invariant wavelet representation algorithm with applications. IEEE Trans Signal Process 44(2):225–232CrossRefGoogle Scholar
  26. 26.
    Liang J, Parks T (1998) Image coding using translation invariant wavelet transforms with symmetric extensions. IEEE Trans Image Process 7:762–769MATHCrossRefMathSciNetGoogle Scholar
  27. 27.
    Mallat S (1989) A theory for multiresolution signal decomposition: the wavelet representation. IEEE Trans Pattern Anal Mach Intell 11(7):674–693MATHCrossRefGoogle Scholar
  28. 28.
    Mallat S (1998) Wavelet tour of signal processing. Academic, USAMATHGoogle Scholar
  29. 29.
    Mallat S, Zhang Z (1993) Matching pursuits with time–frequency dictionaries. IEEE Trans Signal Process 41:3397–3415MATHCrossRefGoogle Scholar
  30. 30.
    Marcellin M, Bilgin A, Gormish M, Boliek M (2000) An overview of JPEG-2000. In: Proceedings of the IEEE data compression conference. IEEE Computer Society, p 523Google Scholar
  31. 31.
    Matsopoulos G, Mouravliansky N, Delibasis K, Nikita K (1999) Automatic retinal image registration scheme using global optimization techniques. IEEE Trans Inf Technol Biomed 3(1):47–60CrossRefGoogle Scholar
  32. 32.
    Pun C, Lee M (2004) Extraction of shift invariant wavelet features for classification of images with different sizes. IEEE Trans Pattern Anal Mach Intell 26(9):1228–1233CrossRefGoogle Scholar
  33. 33.
    Raman B, Wilson M, Benche I, Soliz P (2003) A JAVA-based system for segmentation and analysis of retinal images. In: Proceedings of the IEEE symposium computer-based medical systems, pp 336–339Google Scholar
  34. 34.
    Raudys S, Jain A (1990) Small sample size effects in statistical pattern recognition: recommendations for practitioners and open problems. In: Proceedings of the 10th international conference on pattern recognition, pp 417–423Google Scholar
  35. 35.
    Raudys S, Jain A (1991) Small sample size effects in statistical pattern recognition: recommendations for practitioners. IEEE Trans Pattern Anal Mach Intell 13(3):252–264CrossRefGoogle Scholar
  36. 36.
    Simoncelli E, Freeman W, Adelson E, Heeger D (1992) Shiftable multiscale transforms. IEEE Trans Inf Theory 38:587–607CrossRefMathSciNetGoogle Scholar
  37. 37.
    Sinthanayothin C, Kongbunkiat V, Phoojaruenchanachai S, Singalavanija A (2003) Automated screening system for diabetic retinopathy. In: Proceedings of the 3rd international symposium on image and signal processing and analysis, pp 915–920Google Scholar
  38. 38.
    Tan T (1994) Scale and rotation invariant texture classification. In: IEEE colloquium on texture classification: theory and applications, pp 3/1–3/3Google Scholar
  39. 39.
    Teng T, Lefley M, Claremont D (2002) Progress towards automated diabetic ocular screening: a review of image analysis and intelligent systems for diabetic retinopathy. Med Biol Eng Comput 40(1):2–13CrossRefGoogle Scholar
  40. 40.
    Umbaugh S, Wei Y, Zuke M (1997) Feature extraction in image analysis: a program for facilitating data reduction in medical image classification. IEEE Eng Med Biol Mag 16:62–73CrossRefGoogle Scholar
  41. 41.
    Unser M, Aldroubi A (1996) A review of wavelets in biomedical applications. Proc IEEE 84(4):626–638CrossRefGoogle Scholar
  42. 42.
    Vetterli M, Herley C (1992) Wavelets and filter banks: theory and design. IEEE Trans Signal Process 40(9):2207–2232MATHCrossRefGoogle Scholar
  43. 43.
    Voulgaris G, Jiang J (2001) Texture-based image retrieval in wavelets compressed domain. In: International conference on image processing, pp 125–128Google Scholar
  44. 44.
    Wang T, Karayiannis N (1998) Detection of microcalcifications in digital mammograms using wavelets. IEEE Trans Med Imaging 17:498–509CrossRefGoogle Scholar
  45. 45.
    Wang H, Hsu W, Goh K, Lee M (2000) An effective approach to detect lesions in color retinal images. In: Proceedings of IEEE conference on computer vision and pattern recognition, pp 181–186Google Scholar
  46. 46.
    Xiong Z, Huang T (2002) Wavelet-based texture features can be extracted efficiently from compressed-domain for JPEG2000 coded images. In: International conference on image processing, pp 481–484Google Scholar
  47. 47.
    Zhang H, Fritts J (2004) An overview of JPEG-2000. In: Proceedings of SPIE: visual communications and image processing, pp 1333–1340Google Scholar
  48. 48.
    Zhang E, Zhang Y, Zhang T (2002) Automatic retinal image registration based on blood vessels feature point. In: Proceedings of the international conference on machine learning and cybernetics, pp 2010–2015Google Scholar
  49. 49.
    Zhou P, Wang M, Cao H (2005) Research on features of retinal images associated with hypertension and diabetes. In: Proceedings of IEEE’s international conference on engineering in medicine and biology society, pp 6415–6417Google Scholar

Copyright information

© International Federation for Medical and Biological Engineering 2007

Authors and Affiliations

  1. 1.Department of Electrical and Computer EngineeringRyerson UniversityTorontoCanada

Personalised recommendations