Iris Recognition in Noisy Images

Hits: 0
Research Area: Biometrics
Status: Finished  
Funded by: Fundação para a Ciência e a Tecnologia Funding: 0.00 EUR

Iris biometric algorithms have experienced an important growth and sharpening in their techniques.

However, this expansion is mostly pointed for iris images taken in near-infrared conditions, where subjects have to cooperate in the acquisition process.

Efforts are being made to minimize the trade-off between the quality of the captured data and the recognition accuracy on less constrained environments, where images are obtained at the visible wavelength, at increased imaging distances, over simplified acquisition protocols and adverse lighting conditions.

In this project, we are aiming to achieve the non-cooperative iris recognition from images captured at a distance and on the move, where data is mostly corrupted by noise.