A model based method for retinal blood vessel detection

Vermeer, Koenraad A.; Vos, Frans M.; Lemij, Hans G; Vossepoel, Albert M.

doi:10.1016/s0010-4825(03)00055-6

Cited by 150 publications

(61 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Edge-based methods attempt to identify vessel edges with edge detector, such as Sobel operator [5] and Canny's method [6], morphological detector [7], directional matched differentiator template [4].Kernel-based methods work by convolving images with a filter kernel defined by the model of vessel cross-sectional profile. Blurred half-elliptical profile [8], Gaussian shaped profile [7,9,10], and simple rectangular profile [11] have been proposed for modeling profile crosssections. Based on the idea of fingerprint minutiae [14,15], a robust pattern was first introduced in [2], where a set of landmarks (bifurcations and crossovers of retinal vessel tree) were extracted and used as feature points.…”

Section: Previous Workmentioning

confidence: 99%

Efficient Approach for Retinal Biometric Template Security and Person Authentication using Noninvertible Constructions

Pabitha¹,

Latha²

2013

IJCA

View full text Add to dashboard Cite

Cancelable biometrics is a good approach to address the security and privacy concerns on biometric authentication. The security of cancelable biometrics lies on non invertibility of the transformed templates. So the transforms should be noninvertible and the original biometric template cannot be recovered. Our proposed method initially involves segmentation process to identify blood vessel bifurcation points in the retina, and then the generation of template consisting of the bifurcation points in the blood vessels and the template is transformed using Noninvertible construction (NIC) algorithm and finally matching of the bifurcation points in different patterns. Our work mainly focused to provide the efficient person authentication and the secured biometric template, which has the unique patterns of blood vessels. The effectiveness of our proposed system is then verified with experimental results using a total of 603 retinal images from three different publicly available databases, namely DRIVE, VARIA and STARE. Also we have made a performance analysis, and found that the proposed retinal recognition method gives 100%, 98% and 93% recognition rates, 0%, 0.16%, 0.62% error rates for the above databases and analyzed the Genuine Acceptance Rate (GAR), False Acceptance Rate (FAR) and False Rejection Rate (FAR), Elapsed time respectively. The experimental results obtained using various databases shows that the application of Retinal feature extraction algorithm (RFEA) and NCI results in higher recognition rates and lower error rates.

show abstract

Section: Previous Workmentioning

confidence: 99%

Efficient Approach for Retinal Biometric Template Security and Person Authentication using Noninvertible Constructions

Pabitha¹,

Latha²

2013

IJCA

View full text Add to dashboard Cite

show abstract

“…In the first step, the blood vessels were detected 21 and the NFL at those locations was estimated by interpolating the surroundings of the vessels (see Figure 4a). The image was then transformed into a polar image, as shown in Figure 4b.…”

Section: Edge Detection 3 Matching Edgesmentioning

confidence: 99%

Automated detection of wedge-shaped defects in polarimetric images of the retinal nerve fibre layer

Vermeer

Reus

Vos

et al. 2005

Eye

View full text Add to dashboard Cite

Purpose Automated glaucoma detection in images obtained by scanning laser polarimetry is currently insensitive to local abnormalities, impairing its performance. The purpose of this investigation was to test and validate a recently proposed algorithm for detecting wedge-shaped defects. Methods In all, 31 eyes of healthy subjects and 37 eyes of glaucoma patients were imaged with a GDx. Each image was classified by two experts in one of four classes, depending on how clear any wedge could be identified. The detection algorithm itself aimed at detecting and combining the edges of the wedge. The performance of both the experts and the algorithm were evaluated. Results The interobserver correlation, expressed as ICC(3,1), was 0.77. For the clearest cases, the algorithm yielded a sensitivity of 80% at a specificity of 93%, with an area under the ROC of 0.95. Including less obvious cases by the experts resulted in a sensitivity of 55% at a specificity of 95%, with an area under the ROC of 0.89. Conclusions It is possible to automatically detect many wedge-shaped defects at a fairly low rate of false-positives. Any detected wedge defect is presented in a user-friendly way, which may assist the clinician in making a diagnosis.

show abstract

“…Several models have been presented for fitting retinal vessel intensity profile. Several 1D profile models have been proposed in the litterature: step gate [5], Gaussian [6], mixture of Gaussians [7], Laplacian [8] and Hermite [9][10]. The first two models are simple and widespread, but rather approximate.…”

Section: Introductionmentioning

confidence: 99%

Uncertainty assessment of vessels width measurement from intensity profile model fitting in fundus images

Girard

Kavalec

Tahar³

et al. 2014

Proceedings of the Ophthalmic Medical Image Analysis First International Workshop

View full text Add to dashboard Cite

Abstract. Arteriolar-to-venular diameter ratio (AVR) is an important clinical measurement that allows to characterize retinal vascular abnormalities. A reliable AVR measurement requires accurate and reproducible width measurement. However, in order to measure the vessel width automatically, an approximation of the intensity profile is required by fitting a model. The aim of the proposed study is to assess the uncertainties introduced in the vessel width measurements when choosing a specific distribution as an intensity profile model. Different models are described and an automatic vessel width measurement procedure is presented. The uncertainty introduced by each model is evaluated by computing the standard deviation of the difference between the automatic and the manual measurements. The results show that the intensity profile model should be chosen according to the relative width of the targeted vessels.

show abstract

A model based method for retinal blood vessel detection

Cited by 150 publications

References 8 publications

Efficient Approach for Retinal Biometric Template Security and Person Authentication using Noninvertible Constructions

Efficient Approach for Retinal Biometric Template Security and Person Authentication using Noninvertible Constructions

Automated detection of wedge-shaped defects in polarimetric images of the retinal nerve fibre layer

Uncertainty assessment of vessels width measurement from intensity profile model fitting in fundus images

Contact Info

Product

Resources

About