RT info:eu-repo/semantics/article
T1 Fovea localization in retinal images using spatial color histograms
A1 Sigut Saavedra, José Francisco
A1 Núñez,· Omar
A1 Fumero Batista, Francisco José
A1 Alayón Miranda, Silvia
A1 Díaz Alemán, Tinguaro
A2 Ingeniería Informática y de Sistemas
A2 GAIM (Grupo de Análisis de Imágenes Médicas)
K1 Retinal diseases diagnosis
K1 Fovea localization
K1 Spatial color histogram
AB The automatic location of the fovea is very useful for diagnosing retinal diseases. It isa complex problem for which diferent solutions have been proposed based on classicalimage processing and Deep Learning techniques. The method presented in this paper isbased on histograms that combine spatial and color information in such a way that thespatial coordinates are incorporated into conventional color histograms as an additionaldimension. The binarization of these histograms retains a considerable amount of relevantinformation from the original image, allowing them to be processed as if they were ordinary images. This approach to the problem results in a simple, fast and efective method forlocating the fovea. Diferent experiments have been carried out with three popular sets ofimages: Messidor, REFUGE1 and DIARETDB1, and a comparison was made with otherstate-of-the-art techniques. Our results show that the proposed method, despite its simplicity, is capable of surpassing many of these techniques.
YR 2023
FD 2023
LK http://riull.ull.es/xmlui/handle/915/35089
UL http://riull.ull.es/xmlui/handle/915/35089
LA en
NO https://doi.org/10.1007/s11042-023-16244-6
DS Repositorio institucional de la Universidad de La Laguna
RD 17-jun-2024