Automatic Separation of Retinal Vessels into Arteries and Veins Using Ensemble Learning

N. Ramezani (), H. Pourreza () and O. Khoshdel Borj ()
Additional contact information
N. Ramezani: Islamic Azad University
H. Pourreza: Islamic Azad University
O. Khoshdel Borj: Islamic Azad University

Chapter Chapter 44 in Integral Methods in Science and Engineering, 2015, pp 527-538 from Springer

Abstract: Abstract Separating the retinal vessels into arteries and veins is vital for recognizing the stage of the disease in the diabetics. Precise separation of retinal vessels is highly effective in eyesight improvement of the diabetics. For an appropriate classification of retinal vessels, a proper pre-process, efficient segmentation, extracting distinctive features and using high care classifiers will be essential. The method presented for vessels segmentation in this paper is based on Ensemble Learning whose main goal is to use a number of efficient and complementary classifiers for classifying the characteristics of vessels segments. The results of proposed method are compared with manual labeled Images from VICAVR database. The rate of accuracy of the proposed method equals 95.5% which is the highest value as compared with other methods.

Keywords: Separation of Retinal Vessels; Artery and Vein; Ensemble Learning; Retinex Method; Feature Extraction (search for similar items in EconPapers)
Date: 2015
References: Add references at CitEc
Citations:

There are no downloads for this item, see the EconPapers FAQ for hints about obtaining it.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:sprchp:978-3-319-16727-5_44

Ordering information: This item can be ordered from
http://www.springer.com/9783319167275

DOI: 10.1007/978-3-319-16727-5_44

Access Statistics for this chapter

More chapters in Springer Books from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().