Publication detail

Automatic Extraction of Blood Vessels and Veins using adaptive Filters in Fundus Image

MINAR, J. PINKAVA, M. RIHA, K. DUTTA, M. SINGH, A. TONG, H.

Original Title

Automatic Extraction of Blood Vessels and Veins using adaptive Filters in Fundus Image

Czech Title

Automatická extrakce cév ve fundus obrazech pomocí adaptivních filtrů

English Title

Automatic Extraction of Blood Vessels and Veins using adaptive Filters in Fundus Image

Type

conference paper

Language

en

Original Abstract

The paper proposes a novel method for extraction of blood vessels and veins from medical image of human eye – retinal fundus images that can be used in ophthalmology for detecting various eyes’ diseases such glaucoma, diabetic retinopathy or macula oedema. The method utilizes an approach of preprocessing of image by using adaptive histogram equalization by CLAHE algorithm of green channel of fundus retinal image. Subsequently, using adaptive filters and image convolution with filter mask as key point of proposed algorithm and subsequently is applied the operation erosion processed image and removed small segments from image to enhance extraction of blood vessels from fundus image. The proposed technique analyzes detection and evaluates precision of the method on dataset from public fundus image libraries DRIVE, and HRF and compare with reference training results provided by these libraries.

Czech abstract

Článek popisuje novou metodu pro extrakci cév z medicínských snímků lidského oka-sítnice, tedy z fundus snímků, které lze použít v oftalmologii pro detekci různých očních chorob, jako je glaukom, diabetická retinopatie nebo edém makuly. Tato metoda využívá předzpracování obrazu pomocí ekvalizace histogramu pomocí adaptivního algoritmu CLAHE ze zeleného kanálu fundus snímku. Následně je obraz zpracován pomocí adaptivních filtrů a morfologických operací. Přesnost navržené metody je testována na veřejných databázích fundus snímků DRIVE a HRF.

English abstract

The paper proposes a novel method for extraction of blood vessels and veins from medical image of human eye – retinal fundus images that can be used in ophthalmology for detecting various eyes’ diseases such glaucoma, diabetic retinopathy or macula oedema. The method utilizes an approach of preprocessing of image by using adaptive histogram equalization by CLAHE algorithm of green channel of fundus retinal image. Subsequently, using adaptive filters and image convolution with filter mask as key point of proposed algorithm and subsequently is applied the operation erosion processed image and removed small segments from image to enhance extraction of blood vessels from fundus image. The proposed technique analyzes detection and evaluates precision of the method on dataset from public fundus image libraries DRIVE, and HRF and compare with reference training results provided by these libraries.

Keywords

fundus, retinal, image processing, adaptive filter

Released

27.06.2016

ISBN

978-1-5090-1287-9

Book

39th International Conference on Telecommunications and Signal Processing (TSP)

Pages from

546

Pages to

549

Pages count

4

BibTex


@inproceedings{BUT110778,
  author="Jiří {Minář} and Marek {Pinkava} and Kamil {Říha} and Malay Kishore {Dutta} and Anushikha {Singh} and Hejun {Tong}",
  title="Automatic Extraction of Blood Vessels and Veins using adaptive Filters in Fundus Image",
  annote="The paper proposes a novel method for extraction of blood vessels and veins from medical image of human eye – retinal fundus images that can be used in ophthalmology for detecting various eyes’ diseases such glaucoma, diabetic retinopathy or macula oedema. The method utilizes an approach of preprocessing of image by using adaptive histogram equalization by CLAHE algorithm of green channel of fundus retinal image. Subsequently, using adaptive filters and image convolution with filter mask as key point of proposed algorithm and subsequently is applied the operation erosion processed image and removed small segments from image to enhance  extraction of blood vessels from fundus image. The proposed technique analyzes detection and evaluates precision of the method on dataset from public fundus image libraries DRIVE, and HRF and compare with reference training results provided by these libraries.",
  booktitle="39th International Conference on Telecommunications and Signal Processing (TSP)",
  chapter="110778",
  howpublished="electronic, physical medium",
  year="2016",
  month="june",
  pages="546--549",
  type="conference paper"
}