A fast and accurate personal identification method based on human iris analysis

Iris recognition is one of the most reliable biometric technologies. In this paper, we presented a novel method for iris segmentation using a complex mapping procedure and best-fitting line in the new complex domain. We used an intensity threshold method with Canny edge detector to extract the rough region of the pupil. For the outer boundary a median filter with Prewitt Compass edge detector were used to find the rough region of the outer boundary. By selecting the bottom point of the pupil, which is not usually occluded by the eyelids and eyelashes, as a reference point, two sets of intersecting points between the horizontal lines and pupil's inner and outer boundaries were created. Each point set was map into a new complex domain using the complex inversion map and the best-fitting line was found on the range. Exact inner and outer boundaries of the iris were found by remapping the best-fitting lines to original domain. Lower part of the iris was used in the recognition approach. In order to reduce the feature vector dimensionality, the average of each 4times3 block of extracted 2D iris pattern was calculated and used as new feature information. We tested our proposed method by implementing a ground truth method. Experimental results show that the proposed method has an encouraging performance.