June 14, 2015
June 14, 2015
June 17, 2015
Computing & Information Technology
26.10.1 - 26.10.16
Retina Identification Based on Moment InvariantAbstractIn this paper, we present an algorithm for accurate recognition of an individual’s identity basedon a digitally represented image of the scanned retina. The technology is based upon the fact thatno two retinal patterns are alike.The identification algorithm for three-dimensional retinal imaging is based on using the momentinvariant concept. The mathematical foundation of an invariant feature is related to the theorythat images taken from different angles from the same object have the same set of momentinvariants. Moments contain information of an image which can be used in calculating the locationand orientation of the retinal image.Three-dimensional moment is used as a feature in detecting retinal images, which are modeled asellipsoids. Based on the moment principle, the proposed method can be employed to determinethe nine parameters of an ellipsoidal shape in a retinal image. These nine parameters include thecoordinates of the center of the ellipsoid, the length of major, minor, intermediate axes, and thedirection of three axes. A simulation program for retinal detection is employed.Key Word: Ellipsoid, image processing, pattern recognition, parallel algorithm, Retina, three-dimensional moments.
ASEE holds the copyright on this document. It may be read by the public free of charge. Authors may archive their work on personal websites or in institutional repositories with the following citation: © 2015 American Society for Engineering Education. Other scholars may excerpt or quote from these materials with the same citation. When excerpting or quoting from Conference Proceedings, authors should, in addition to noting the ASEE copyright, list all the original authors and their institutions and name the host city of the conference. - Last updated April 1, 2015