Retinal image registration using creases as anatomical landmarks

David Lloret, Joan Serrat, Antonio M. López, Andrés Soler, Juan J. Villanueva

    Producció científica: Contribució a una revistaArticleRecercaAvaluat per experts

    17 Cites (Scopus)


    Retinal images are routinely used in ophthalmology to study the optical nerve head and the retina. To assess objectively the evolution of an illness, images taken at different times must be registered. Most methods appeared so far have been designed specifically for a single image modality, like temporal series or stereo pairs of angiographies, fluorescein angiographies or SLO images, which makes them prone to fail when conditions vary. In contrast, the method we propose has shown to be accurate and reliable on all the former modalities. Actually, it has been adapted from the 3D registration of CT and MR image to 2D. Relevant features (also known as landmarks) are extracted by means of a robust creaseness operator, and resulting images are iteratively transformed until a maximum in their correlation is achieved. Our method has succeed in more than 100 pairs tried so far, in all cases including also the scaling as a parameter to be optimized. © 2000 IEEE.
    Idioma originalEnglish
    Pàgines (de-a)203-206
    RevistaProceedings - International Conference on Pattern Recognition
    Estat de la publicacióPublicada - 1 de des. 2000


    Navegar pels temes de recerca de 'Retinal image registration using creases as anatomical landmarks'. Junts formen un fingerprint únic.

    Com citar-ho