enhancement of retinal fundus image using 2-d gabor wavelet transform

33
Enhancement Of Retinal Fundus Image Using 2-D GABOR WAVELET Transform Monika Rout 1

Upload: monika-rout

Post on 02-Jun-2015

420 views

Category:

Education


0 download

DESCRIPTION

What Is GABOR Wavelet & Why we need this with mathematical descriptions

TRANSCRIPT

  • 1. Monika Rout1

2. OVER VIEW: Fundus Image Image Enhancement 2D Gabor wavelet method Morphological approach Evaluation GUI Conclusion2 3. Objectives: Enhancement of Retinal fundus Image:(a)2D Gabor Wavelet transform (b)Morphological method Database Required: (a)STARE database (b)DRIVE database Evaluation of the image calculated: (a)Universal Quality Index (b)Structure Similarity Index 3 4. Introduction.. What Is Fundus Image??? The fundus of the eye is the interior surface of the eye,opposite the lens, and includes the retina and optic disc.4 5. 5 6. What Is GABOR Wavelet & Why??? A nonlinear filtering approach is used to enhance the bloodvessels by measuring the vessel width from the retinal fundus image. Gabor Wavelet is a Gaussian modulated function by acomplex sinusoid.6 7. Where, is the standard deviations of the Gaussian function is frequency. is generating function.7 8. 8 9. Why Unsharp masking ???9 10. METHODOLOGY:10 11. WHAT IS MORPHOLOGY ??? Morphological image processing is used to extract image components for representation and description of region shape, such as boundaries, skeletons. Structure elements : Small sets or sub-images used to probe an image under study for properties of interest 11 12. Top-hat transformation Purpose:i.detect structures of a certain size. ii.light objects on a dark background (also called white top-hat). Th(f) = f-(f b) Where,f = original image b= Structuring element = opening operator 12 13. Ref: Gonzalez and woods,ch-913 14. Bottomhat Transform: Purpose: i.detect structures of a certain size. ii. dark objects on a bright background (also called black top-hat) Bh(f) = (f b)-f Where, f = original image b= Structuring element = closing operator 14 15. Example of bottom-hat :15 16. METHODOLOGY:16 17. Performance Evaluation Parameters: Universal Quality Index Measure (UQIM) Structure Similarity Index Measure (SSIM)17 18. UQIM approach:18 19. 19 20. 20 21. 21 22. MODELLING OF Q :22 23. SSIM approach:23 24. For luminance measurement:l (x, y )2x2 xy 2 yC1 C1Where,C1is constant x andyare the mean/average of signals x and y .24 25. For contrast measurement:-HereC2is constant x-Standard deviation of xy -Standard deviation of y- variance of x - variance of y 25 26. For structure measurement:C3xys(x, y) xyC3WhereC3is constantxy -correlation of x and y x -Standard deviation of x y-Standard deviation of y26 27. MODELLING OF S :27 28. WHAT IS GUI??? (graphical user interface) M-files FIG-files28 29. INPUT IMAGE OF DRIVE DATABASE29 30. PROPOSED METHODOLOGY:[Implementation methodology of retinal image enhancement] 30 31. SERIAL NO.OBJECTIVES1STATUSLiterature Survey i. 2D-gabor wavelet ii. Morphology approachCompletediii.QUIM and SSIM 2CompletedCompletedCoding i.GUIPartly Completed31 32. REFERENCES: [1] T. S. Lee, Image representation using 2D Gabor wavelets, IEEE Trans. Pattern Anal.Mach. Intell., vol. 18, no. 10, pp. 959971, Oct. 1996. [2] Subrahmanyam Murala, Anil Balaji Gonde, R.P. Maheshwari, Color and texture featuresfor image indexing and retrieval, IEEE International Advance Computing Conference (IACC2009) [3] J. Serra. Image analysis using mathematical morphology . Academic Press, London, 1982. [4] R. C. Gonzalez and R. E. Woods, Digital image processing, Prentice hall, second edition,2002. [5] Zhou Wang and Alan C. Bovik, A Universal Image Quality Index IEEE SignalProcessing Letters Vol 9,pp 81-84March 2002. [6] Zhou Wang and Eero Simoncelli, Image Quality Assesment: From Error Visibility toStructural Similarity,IEEE Transactions on Image Processing,April 2004. [7] With the help of Internet32 33. THANK YOU.33