This paper presents a new human identification system based on the features obtained from retina images using angular partitioning and radial partitioning. The proposed algorithm is composed of two principal modules including feature extraction and comparison between extracted features and decision making. In the feature extraction stage, first all of the images are normalized by applying a preprocessing. Then, the blood vessel’s pattern is extracted from retina images and a morphological thinning process is applied on the extracted pattern. Then two feature vectors based on the angular partitioning and radial partitioning are are extracted from the retina pattern. The extracted features are rotation and scale invariant and robust against translation. In the next stage, these feature vectors are analyzed using 1D discrete Fourier transform and the Manhattan metric is used to measure the closeness of the feature vectors to have a compression on them. Experimental results on a database, including 360 retina images obtained from 40 subjects, demonstrated an average true accuracy rate equal to 98.5 percent for the proposed identification system.
