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.

In this article, we propose a new method for localizing optic disc in retinal images. Localizing the optic disc and its center is the first step of most vessel segmentation, disease diagnostic, and retinal recognition algorithms. We use optic disc of the first four retinal images in DRIVE dataset to extract the histograms of each color component. Then, we calculate the average of histograms for each color as template for localizing the center of optic disc. The DRIVE, STARE, and a local dataset including 273 retinal images are used to evaluate the proposed algorithm. The success rate was 100, 91.36, and 98.9%, respectively.

This paper presents a new approach for iris localization which consists of one of the most important steps in an iris recognition system. We have solved some of the most important drawbacks of the current methods using a pointwise level set algorithm, which detects the precise location of the iris by a stepwise deformation of an initial contour. Due to the special properties of our approach, there is no constraint about angles of head tilt. Furthermore, this algorithm is robust in noisy situations and can find irises which are partly occluded by eyelid and eyelashes. This is done by using a topology preserving technique in only one step to find both inner and outer boundaries. Another advantage of our method is its ability to find iris in images which include other parts of face. This pointwise level set approach makes it possible to perform the operations of the iris localization and mapping of iris coordinates to a polar dimension simultaneously, an approach which decreases the processing time of the system considerably. The experimental results show that the proposed method outperforms the current methods both in terms of accuracy and response time.

This paper presents a new human recognition method based on features extracted from retinal images. The proposed method is composed of some steps including feature extraction, phase correlation technique, and feature matching for recognition. In the proposed method, Harris corner detector is used for feature extraction. Then, phase correlation technique is applied to estimate the rotation angle of head or eye movement in front of a retina fundus camera. Finally, a new similarity function is used to compute the similarity between features of different retina images. Experimental results on a database, including 480 retinal images obtained from 40 subjects of DRIVE dataset and 40 subjects from STARE dataset, demonstrated an average true recognition accuracy rate equal to 100% for the proposed method. The success rate and number of images used in the proposed method show the effectiveness of the proposed method in comparison to the counterpart methods.

No abstract