Extraction and Shape Description of Feature Region on Ocular Fundus Fluorescein Angiogram

형광 안저화상에 관한 특수 영역의 유출 및 모양

An image feature extraction method for the low contrast fluoresceln angiogram in dlabetes was studied. To obtain effective image segmentation, an adaptive local difference image is generated and relaxation process are applied to this difference Image. By the use of distance transformed data with segmented image, shape and location of feature regions were obtained. It was shown that the location and shape descriptions of Impaired blood vessel networks and retinal regions are can he utilized for the diagnosis of diabetes and other disease.