In order to assist the diagnoses of fundus diseases and some cardiovas cular diseases,this paper proposes a fundus image blood vessel segmentation method via joint dictionary learning an d multi-scale line structure detection.Firstly,brightness is adjusted and balanced by gamma correction in H SV color space,contrast is improved via CLAHE algorithm in Lab color space,and multi-scale line structure detection algorithm is used to enhance the blood vessel structures and get the feature maps.Then,the represen tation dictionary and segmentation dictionary are trained simultaneously by K-SVD algorithm from the feature block s and its corresponding manually annotated vessel label blocks.The reconstructed sparse coefficients of ne wly input enhanced feature blocks are obtained with the representation dictionary,and the blood vessel blocks are segmented by these coefficients and segmentation dictionary.Finally,the blood vessel result is obtained via im age blocks stitching,noise removal and hole filling algorithms.Our method is tested on DRIVE and HRF databases to evaluate the segmentation performance in accuracy,sensitivity,specificity and other five metr ics.The average accuracy rate reaches 0.9582and 0.9515respectively,the average specificity reaches 0.9826and 0.9671respectively,the average sensitivity reaches 0.7095and 0.7626respectively,which indicates that our method has good segmentation performance and versatility.