Identification of retinal vessels by color image analysis

• Autorzy: Rakotomalala V. , Macaire L. , Postaire J. G. , Valette M.
• Języki publikacji: EN

Abstrakty

EN

A recursive edge tracking of the retinal blood vessel is presented in order to achieve a bidimensionnal reconstruction of the rential vasculature. First, color edge detection is applied on the original angiographic images. Second, from interactive selection of starting points near the papilla, the tracking of the two contours of a vessel is processed. The algorithm validates the next connected pixels to the current ones which satisfy the tracking hypotheses. Problems induced by the curvature of the vessel and the discontinuity of the detected edges will be dealed with. Third, during the tracking procedure is then performed from these branch points until the end of the vessel is reached. Contour and the color of the vessel's body are associated in order to get more accurate extraction. The reconstructed vacular strucures will be used as landmarks for the follow--up of a new retinopathy called CytoMegalo Virus retinitis found on patients with acquired immune deficiency syndrome (AIDS).

Słowa kluczowe

EN

color image processing; color gradient; blood vessel reconsttruction; edge tracking; color region/edge cooperation

• Wydawca: Institute of Information Technology of the Warsaw University of Life Sciences – SGGW
• Czasopismo: Machine Graphics and Vision
• Rocznik: 1998
• Tom: Vol. 7, No. 4
• Strony: 725--742
• Opis fizyczny: Bibliogr. 17 poz.

Twórcy

autor

Rakotomalala V.

autor

Macaire L.

autor

Postaire J. G.

autor

Valette M.

• Ecole des Mines de Douai, Departement Productique, 59508 DOUAI Cedex, France