This paper presents a novel biometric identification system with high performance based on the features obtained from human retinal images. This system is composed of three principal modules including blood vessel segmentation, feature generation, and feature matching. Blood vessel segmentation module has the role of extracting blood vessels pattern from retinal images. Feature generation module includes the following stages. First, the optical disk is found and a circular region of interest (ROI) around it is selected in the segmented image. Then, using a polar transformation, a rotation invariant template is created from each ROI. In the next stage, these templates are analyzed in three different scales using wavelet transform to separate vessels according to their diameter sizes. In the last stage, vessels position and orientation in each scale are used to define a feature vector for each subject in the database. For feature matching, we introduce a modified correlation measure to obtain a similarity index for each scale of the feature vector. Then, we compute the total value of the similarity index by summing scale-weighted similarity indices. Experimental results on a database, including 300 retinal images obtained from 60 subjects, demonstrated an average equal error rate equal to 1 percent for our identification system.