An Algorithm for Retinal Feature Extraction Using Hybrid Approach

Panchal, Parth; Bhojani, Ronak; Tp,

doi:10.1016/j.procs.2016.03.009

Cited by 21 publications

(14 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Rule-based methods incorporate methods for retinal blood vessel segmentation that are based on mathematical morphology, line detection, various transforms, etc. Examples of these kinds of blood vessel segmentation methods are [1], [12], [20], [22], [23], [24], [29], [34] and [35]. Nguyen et al [24] used multi-scale line detection for retinal blood vessel segmentation in order to avoid the drawbacks of the basic line detector.…”

Section: Related Workmentioning

confidence: 99%

“…width or length). Panchal et al [29] presented an algorithm for retinal feature extraction and some of the methods that they used were edge detection, thinning operation, and scanning window (of size 3x3 pixels) analysis that searched for ridges and bifurcations. Hatanaka et al [12] proposed a blood vessel detection method that used a square double ring filter.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Retinal blood vessel segmentation based on heuristic image analysis

2019

View full text Add to dashboard Cite

Automatic analysis of retinal fundus images is becoming increasingly present today, and diseases such as diabetic retinopathy and age-related macular degeneration are getting a higher chance of being discovered in the early stages of their development. In order to focus on discovering those diseases, researchers commonly preprocess retinal fundus images in order to detect the retinal landmarks -blood vessels, fovea and the optic disk. A large number of methods for the automatic detection of retinal blood vessels from retinal fundus images already exists, but many of them are using unnecessarily complicated approaches. In this paper we demonstrate that a reliable retinal blood vessel segmentation can be achieved with a cascade of very simple image processing methods. The proposed method puts higher emphasis on high specificity (i.e. high probability that the segmented pixels actually belong to retinal blood vessels and are not false positive detections) rather than on high sensitivity. The proposed method is based on heuristically determined parametric edge detection and shape analysis, and is evaluated on the publicly available DRIVE and STARE datasets on which it achieved the average accuracy of 96.33% and 96.10%, respectively.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Retinal blood vessel segmentation based on heuristic image analysis

2019

View full text Add to dashboard Cite

show abstract

“…By utilization of biometrics, it is conceivable to accomplish this abnormal state of security necessities in the offices referenced previously. For this paper, we will focus on the utilization of retinal scans as methods for recognizable proof and the retina as the biometric (Panchal, Bhojani & Panchal 2016;Modarresi, Oveisi & Janbozorgi, 2017).…”

Section: Introductionmentioning

confidence: 99%

Study of Feature Extraction of Retinal Scans

Abdulhamid

Muthomi

2019

Scientific Bulletin

View full text Add to dashboard Cite

In this paper, the retina is discussed as part of the feature of extraction of retinal scans for use in security systems as a means of identification. The design system contains a method of image acquisition and processing of the image. A computer system is also incorporated for matching and verifying the image captured to an already present representation of unique features of the retina that are stored as templates for matching and identification. It should then either allow or deny the user depending on the results of the matching process. This paper shows the development of the step undertaken to process the image to the extraction of the features. The high resolution images are taken through a series of image enhancement process before feature extraction technics are applied and before templates are created for future referencing. The main limitation of this process is attributed to capturing the image from the retina. The image obtained may be of poor quality thus making the unique features of the retina unclear.

show abstract

“…Albeit retinal examples might be changed if there should be an occurrence of sicknesses, for example, glaucoma, diabetes, and auto insusceptible proficiency disorder, the retina remains normally stable over a man's lifetime [14]. The execution of retina based biometric frameworks is considered as the best in term of precision [15]. In addition, human retina has not yet been fashioned and the retina of dead people rots too quickly to ever be utilized to swindle a retinal sweep [16].…”

Section: Introductionmentioning

confidence: 99%

A Novel Retinal Recognition System for Pathological Retina To Enhance Security

Rani¹,

Rani²

2018

IJET

View full text Add to dashboard Cite

Biometric acknowledgment gives a characteristic and solid answer for the issue of individual distinguishing proof. One of the biometric ID framework utilized with high exactness is the retinal verification as a result of its many-sided quality in spoofing. However in these frameworks, acknowledgment rate is enormously influenced by the vasculature multifaceted nature of retinal images. This vascular example turns out to be exceptionally perplexing in sick retinal pictures because of the nearness of obsessive signs. In this manner, we require a computerized productive calculation which can evacuate these abnormalities before matching and decision making. The proposed novel hybrid clustering algorithm Adaptive Weighted Neighbour (AWN) Classification Algorithm classifies the input retinal image based on the features extracted and match the features with the trained features. The proposed feature vector consists of blood vessel structure, bifurcation points, bifurcation angles and vessel width. Results from the AWN are compared with state of the art classifier. It enables high security, good performance and greater accuracy. Also it provides better FAR, FRR and decreases the error rate.

show abstract

An Algorithm for Retinal Feature Extraction Using Hybrid Approach

Cited by 21 publications

References 12 publications

Retinal blood vessel segmentation based on heuristic image analysis

Retinal blood vessel segmentation based on heuristic image analysis

Study of Feature Extraction of Retinal Scans

A Novel Retinal Recognition System for Pathological Retina To Enhance Security

Contact Info

Product

Resources

About