Automatic extraction of retinal vessels based on gradient orientation analysis

Onkaew, Danu; Turior, Rashmi; Uyyanonvara, Bunyarit; Kondo, Toshiaki

doi:10.1109/jcsse.2011.5930102

Cited by 12 publications

(6 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, the blood vessels are localized by finding the discontinuities in the gradient orientation. The feature extraction depends on the orientation of the gradient vector field not its magnitude; therefore, it is robust against low contrast and nonuniform illumination [26].…”

Section: ) Orientation Analysis Of a Gradient Vector Fieldmentioning

confidence: 99%

An Ensemble Classification-Based Approach Applied to Retinal Blood Vessel Segmentation

Fraz

Remagnino

Hoppe

et al. 2012

IEEE Trans. Biomed. Eng.

Self Cite

812

383

View full text Add to dashboard Cite

Abstract-This paper presents a new supervised method for segmentation of blood vessels in retinal photographs. This method uses an ensemble system of bagged and boosted decision trees and utilizes a feature vector based on the orientation analysis of gradient vector field, morphological transformation, line strength measures, and Gabor filter responses. The feature vector encodes information to handle the healthy as well as the pathological retinal image. The method is evaluated on the publicly available DRIVE and STARE databases, frequently used for this purpose and also on a new public retinal vessel reference dataset CHASE_DB1 which is a subset of retinal images of multiethnic children from the Child Heart and Health Study in England (CHASE) dataset. The performance of the ensemble system is evaluated in detail and the incurred accuracy, speed, robustness, and simplicity make the algorithm a suitable tool for automated retinal image analysis.

show abstract

Section: ) Orientation Analysis Of a Gradient Vector Fieldmentioning

confidence: 99%

An Ensemble Classification-Based Approach Applied to Retinal Blood Vessel Segmentation

Fraz

Remagnino

Hoppe

et al. 2012

IEEE Trans. Biomed. Eng.

Self Cite

812

383

View full text Add to dashboard Cite

show abstract

“…However, a couple of them are shown better results compared to the proposed methodology that stated in the literature review. There are few studies which have attempted to adjust the illumination variation of the fundus images [1] [4] [5] [10]. The proposed methodology has the highest sensitivity and the accuracy when comparing the statistical data with the previous approaches [18]- [22].…”

Section: Resultsmentioning

confidence: 99%

An Improved Method for Automatic Retinal Blood Vessel Vascular Segmentation Using Gabor Filter

Karunanayake¹,

Kodikara²

2015

OJMI

View full text Add to dashboard Cite

Early detection of Non-Proliferative Diabetic Retinopathy (NDPR) is currently a highly interested research area in biomedical imaging. Ophthalmologists discover NDPR by observing the configuration of the vessel vascular network deliberately. Therefore, a computerized automatic system for the segmentation of vessel system will be an assist for ophthalmologists in order to detect an early stage of retinopathy. In this research, region based retinal vascular segmentation approach is suggested. In the steps of processing, the illumination variation of the fundus image is adjusted by using the point operators. Then, the edge features of the vessels are enhanced by applying the Gabor Filter. Finally, the region growing method with automatic seed point selection is used to extract the vessel network from the image background. The experiments of the proposed algorithm are conducted on DRIVE dataset, which is an open access dataset. Results obtain an accuracy of 94.9% over the dataset that has been used.

show abstract

“…The study was tested on the DRIVE and STARE databases and obtained an average 94.76% accuracy for the DRIVE database and 95.79% accuracy for the STARE database. Another study conducted by Onkaew et al [24] through gradient orientation analysis method obtained an average 93.58% accuracy for the DRIVE database and 94.23% for the STARE database. Fraz et al [25] conducted a segmentation study based on morphological curvature and adapted hysteresis thresholding.…”

Section: Introductionmentioning

confidence: 92%

A novel approach for automatic blood vessel extraction in retinal images: complex ripplet-I transform and complex valued artificial neural network

Ceylan¹,

Yaşar²

2016

Turk J Elec Eng & Comp Sci

View full text Add to dashboard Cite

This study determined the features of line, curve, and ridge structures in images using complex ripplet-I and enabled extraction of blood vessel networks from retinal images through a complex valued artificial neural network using those features. Forty color fundus images in the DRIVE database and 20 color fundus images in the STARE database were used to test the success of the proposed system. In this study, a complex version of ripplet-I transform was used for the first time. By presenting the directed image for the determination of the unique geometrical properties of the vessel regions, complex ripplet-I transforms showing better performance than other types of multiresolution analysis were combined with a complex valued ANN. The results in the study were reobtained using leave-one-out crossvalidation method with bagging technique in order to ensure the stability and correctness of the performance. In the DRIVE database, the highest average accuracy of the system was found to be 98.44% for complex ripplet-I transform and complex valued ANN. For the STARE database (labeled by Adam Hoover), highest average accuracy rates were obtained as 99.25% for complex ripplet-I transforms and complex valued ANN. Similarly, for the other labeled data (by Valentina Kouznetsova), highest average accuracy rates were obtained as 98.03% for complex ripplet-I transforms and complex valued ANN.

show abstract

Automatic extraction of retinal vessels based on gradient orientation analysis

Cited by 12 publications

References 8 publications

An Ensemble Classification-Based Approach Applied to Retinal Blood Vessel Segmentation

An Ensemble Classification-Based Approach Applied to Retinal Blood Vessel Segmentation

An Improved Method for Automatic Retinal Blood Vessel Vascular Segmentation Using Gabor Filter

A novel approach for automatic blood vessel extraction in retinal images: complex ripplet-I transform and complex valued artificial neural network

Contact Info

Product

Resources

About