Aiming at the problem that the detection accuracy is not high for most retinal exudates detection algorithms,a retinal exudates detection algorithm fu sing the reconstruction filters and dark features is proposed. Firstly,the mean filter is applied to the retinal grayscale image before the ‘ball’ reconstruction filter is conducted to remove the blood vessels,the column filter is used to mark the ex udates region,and the exudates region image with the optic disc and borders is obtained after thresholding seg mentation.Secondly,the optic disc and image borders are detected in grayscale image with the mean filter applied,and the mask is created based on the optic disk,then the optic disc and borders are removed from the exudate s region image containing the optic disc and borders,after which the ‘disk’ re construction filter is implemented to expand the exudates sizes. Finally,the retinal grayscale image is applied with adaptive histogram equaliz ation,dark features are extracted with intensity reversion after binarizing the image by thresholding,and the fina l image of exudates is obtained after removing the dark features from the image with expanded exudates′ sizes.The exp erim ent results indicate that the proposed algorithm can effectively detect the exudates of retinal fundus image, and it also has high detection accuracy.