전안부 영상에서의 동공 및 홍채 영상 분할 연구
A Study on Pupil and Iris Segmentation of the Anterior Segment of the Eye
0
조회
0
다운로드
5
인용
0
참고문헌
키워드
초록
Objective: The goal of this study was to develop a novel pupil and iris segmentation algorithm. We evaluated segmentation performance based on a fractal model. Two methods were compared: Daugman’s and our new proposed method. Methods: We received 200 anterior segment images with 3,872×2,592 pixels. Here we present an active contour model that accurately detects pupil boundaries in order to improve the performance of segmentation systems. We propose a method that uses iris segmentation based on a fractal model. We compared the performance of Daugman's method and the proposed new method and statistically analyzed the results. Results: We manually compared segmentation with the Daugman’s method and the new proposed method. The findings showed that the proposed segmentation accuracy was about 2.5 percent higher than Daugman's method. There was a significant difference (p<0.05) between the under and over data between the two methods. Conclusion: The results of this study show that the new proposed method was more accurate than the conventional method for the measurement of segmentation of the eye by CAD (Computer-aided Diagnosis)
Abstract
Objective: The goal of this study was to develop a novel pupil and iris segmentation algorithm. We evaluated segmentation performance based on a fractal model. Two methods were compared: Daugman’s and our new proposed method. Methods: We received 200 anterior segment images with 3,872×2,592 pixels. Here we present an active contour model that accurately detects pupil boundaries in order to improve the performance of segmentation systems. We propose a method that uses iris segmentation based on a fractal model. We compared the performance of Daugman's method and the proposed new method and statistically analyzed the results. Results: We manually compared segmentation with the Daugman’s method and the new proposed method. The findings showed that the proposed segmentation accuracy was about 2.5 percent higher than Daugman's method. There was a significant difference (p<0.05) between the under and over data between the two methods. Conclusion: The results of this study show that the new proposed method was more accurate than the conventional method for the measurement of segmentation of the eye by CAD (Computer-aided Diagnosis)
참고문헌 (16)
- Lim JI, "A comparisonof digital nonmydriatic fundus imaging with standard35-millimeter slides for diabetic retinopathy", Ophthalmology, 107(5), pp.866~870 (2000)
- Yen KG, "The optimum time to employ telephoto screening to detect retinopathy of prematurity", Trans Am Ophthalmol Soc, 98, pp.145~150 (2000)
- van Norren D, "Retinal densitometerwith the size of a fundus camera", Vision Res, 29(3), pp.369~374 (1989)
- Tuulonen A, "Screening for glaucoma with a non-mydriatic funduscamera", Acta Ophthalmol (Copenh), 68(4), pp.445~449 (1990)
- Zeimer R, "Afundus camera dedicated to the screening of diabeticretinopathy in the primary-care physician's office", Invest Ophthalmol Vis Sci, 43(5), pp.1581~1587 (2002)
- Gili Manzanaro P, "Digital analysis ofthe optic disc with fundus camera: a study of variability", Arch Soc Esp Oftalmol, 79(3), pp.125~130 (2004)
- Schmitz-Valckenberg S, "Evaluation ofautofluorescence imaging with the scanning laserophthalmoscope and the fundus camera in age- relatedgeographic atrophy", Am J Ophthalmol, 146(2), pp.183~192 (2008)
- Daugman J, "High confidence Recognition of Persons byRapid Analysis of Iris Texture", IEEE Conference Publication, 통권 : 408, pp.244~251 (1995)
- Daugman J, "New methods in iris recognition", IEEE Trans Syst Man Cybern B Cybern, 37(5), pp.1167~1175 (2007)
- Huang H, "Iris recognition based on adjustablescale wavelet transform", Conf Proc IEEE Eng Med BiolSoc, 통권 : 7, pp.7533~7536 (2005)
- Monro DM, "Rakshit S, Zhang D. DCT-based irisrecognition", IEEE Trans Pattern Anal Mach Intell, 29(4), pp.586~595 (2007)
- Klemencic A, "Automatedsegmentation of muscle fiber images using activecontour models", Cytometry, 32(4), pp.317~326 (1998)
- Bogdanova I, "Vandergheynst P.Scale space analysis and active contours foromnidirectional images", IEEE Trans Image Process, 16(7), pp.1888~1901 (2007)
- Parker JR, "Algorithms for image processing andcomputer vision" (1997), WILEY COMPUTER PUBLISHING
- Gonzalez RC, "Digital image processing using Mat Lab" (2004), ITC
- Otsu N, "A threshold selection method from gray_level histograms", IEEE Trans Systems Man and Cybernetics, 통권 : 79, pp.62~66 (1979)