Author(s):
T. Pearson, G. Manogna, K. Prathima, P. Roshini Mary
Email(s):
prathimareddyk97@gmail.com
DOI:
10.5958/2321-581X.2019.00014.X
Address:
Dr. T. Pearson1, G. Manogna2, K. Prathima2, P. Roshini Mary2
1Professor in, Dept. of Electronics Communication and Engineering, SPEC, Hyderabad,
2Final Year Students of Electronics Communication and Engineering, SPEC, Hyderabad.
*Corresponding Author
Published In:
Volume - 10,
Issue - 2,
Year - 2019
ABSTRACT:
Examining the eye could be as efficacious as physical one in determining health concerns. Screening the retina is the initial step to detect the hidden health issues which even includes pre-diabetes and diabetes. By clinical diagnosis and prognosis, ophthalmologists depend highly on the binary segmented version of retina fundus image, where the accuracy of segmented vessels, optic disc and abnormal lesions extremely affects the diagnosis accuracy which in turn affects the subsequent clinical treatment steps. This paper proposes an automated retinal fundus image segmentation system which consists of three segmentation subsystems and follows same core segmentationalgorithm. Despite of broad difference in features and characteristics; retinal vessels, optic disc and exudate lesions are extracted by each subsystem without the need for texture analysis or synthesis. In order to obtain complete clinical insight and avoid complexity with the existing techniques, our proposed system can detect these anatomical structures using one session with great accuracy even in pathological retina images. The proposed system uses a robust hybrid segmentation algorithm that combines adaptive fuzzy thresholding and mathematical morphology. The system is justified by using four benchmark datasets which are DRIVE and STARE (vessels), DRISHTI-GS (optic disc), and DIARETDB1 (exudates lesions). By adopting these algorithms competitive segmentation performance is achieved out by performing a variety of up-to-date systems and demonstrating the capacity to deal with other heterogeneous anatomical structures.
Cite this article:
T. Pearson, G. Manogna, K. Prathima, P. Roshini Mary. Retinal Structure Segmentation using Adaptive Fuzzy Thresholding. Research J. Engineering and Tech. 2019;10(2):74-82. doi: 10.5958/2321-581X.2019.00014.X
Cite(Electronic):
T. Pearson, G. Manogna, K. Prathima, P. Roshini Mary. Retinal Structure Segmentation using Adaptive Fuzzy Thresholding. Research J. Engineering and Tech. 2019;10(2):74-82. doi: 10.5958/2321-581X.2019.00014.X Available on: https://ijersonline.org/AbstractView.aspx?PID=2019-10-2-4