Abstract

Human retinal blood vessel images possess certain charac- teristics that are suitable for personal identification and other advanced security applications. We propose an image processing algorithm for matching retinal blood vessel patterns based on the locations of inter- sections of blood vessels. The algorithm includes preprocessing, orien- tation registration, and similarity measurement. Preliminary experimental results show that our method achieves good discrimination among im- ages from different subjects. © 2003 Society of Photo-Optical Instrumentation En- gineers. (DOI: 10.1117/1.1613278)

Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call