| Resumen |
The retinal vascular network has many desirable characteristics to
be used as a basis for personal authentication, including uniqueness, stability, and permanence. In this paper a new approach for retinal image structural features extraction from the vascular network and template coding is proposed.
The use of a logarithmic spiral grid for scanning and tracking the vascular network and the SAX representation of the time series technology conform the key to make this new approach simple, flexible and reliable. Experiments show that with this approach we can achieve the reduction of the data dimensionality and the time required to obtain a valid biometric code from the vascular network of retinal images for authentication purposes. |
