Detection and measurement of retinal vessels in fundus images using amplitude modified second-order Gaussian filter

Liu, Gang; Chutatape, O.; Krishnan, Shankar

doi:10.1109/10.979356

Cited by 264 publications

(119 citation statements)

References 10 publications

Supporting

Mentioning

109

Contrasting

Unclassified

Order By: Relevance

“…In Hoover's algorithm [20] a piece of the blood vessel network is hypothesized by probing an area of the matched-filter response image and, while doing so, the threshold on the matched filter is iteratively decreased. Gang et al [17] proposes an amplitude-modified second-order derivative of a Gaussian filter to detect vessels at scales that match their widths. Steerable filters are introduced in [14] and extended in [54].…”

Section: Introductionmentioning

confidence: 99%

Retinal Vessel Centerline Extraction Using Multiscale Matched Filters, Confidence and Edge Measures

Sofka

Stewart

2006

IEEE Trans. Med. Imaging

312

184

View full text Add to dashboard Cite

Motivated by the goals of improving detection of low-contrast and narrow vessels and eliminating false detections at non-vascular structures, a new technique is presented for extracting vessels in retinal images. The core of the technique is a new likelihood ratio test that combines matchedfilter responses, confidence measures and vessel boundary measures. Matched filter responses are derived in scale-space to extract vessels of widely varying widths. A vessel confidence measure is defined as a projection of a vector formed from a normalized pixel neighborhood onto a normalized ideal vessel profile. Vessel boundary measures and associated confidences are computed at potential vessel boundaries. Combined, these responses form a 6-dimensional measurement vector at each pixel. A training technique is used to develop a mapping of this vector to a likelihood ratio that measures the "vesselness" at each pixel. Results comparing this vesselness measure to matched filters alone and to measures based on the Hessian of intensities show substantial improvements both qualitatively and quantitatively. The Hessian can be used in place of the matched filter to obtain similar but less-substantial improvements or to steer the matched filter by preselecting kernel orientations. Finally, the new vesselness likelihood ratio is embedded into a vessel tracing framework, resulting in an efficient and effective vessel centerline extraction algorithm.

show abstract

Section: Introductionmentioning

confidence: 99%

Retinal Vessel Centerline Extraction Using Multiscale Matched Filters, Confidence and Edge Measures

Sofka

Stewart

2006

IEEE Trans. Med. Imaging

312

184

View full text Add to dashboard Cite

show abstract

“…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

“…The main cause of visual impairment and blindness in ROP is retinal detachment which is the subsequence of the scars in turn. Swollen and twisted veins contribute to Plus-disease (PD) that is considered as the most severe type of ROP [4]. In Figure 1, retinal detachment of scleral membrane due to the stretching of the wound contraction caused by abnormal blood vessel growth is shown.…”

Section: Introductionmentioning

confidence: 99%

Comparison of Filtering and Clustering Techniques in Diagnosis of Infants Retinopathy Risk

Hormozi¹,

Monadjemi²,

Naderian³

2014

Computer Science &Amp; Information Technology ( CS &Amp; IT )

View full text Add to dashboard Cite

ROP is an eye disease in premature infants. In infants who are born earlier than normal, retinal vessel growth stops. Early treatment is very crucial in this case as it can end up to blindness if the diagnosis has not done in a short time. The purpose of this research is to design an intelligent automated system for the early detection of disease at an early stage to prevent these babies from dangerous consequences. In this study, we analyzed the images in the Lab

show abstract

Detection and measurement of retinal vessels in fundus images using amplitude modified second-order Gaussian filter

Cited by 264 publications

References 10 publications

Retinal Vessel Centerline Extraction Using Multiscale Matched Filters, Confidence and Edge Measures

Retinal Vessel Centerline Extraction Using Multiscale Matched Filters, Confidence and Edge Measures

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

Comparison of Filtering and Clustering Techniques in Diagnosis of Infants Retinopathy Risk

Contact Info

Product

Resources

About