PROJECT TITLE :

Negative Iris Recognition - 2018

ABSTRACT:

Components of someone's biometrics are usually stable over the duration of a lifetime, and therefore, it is highly important to shield biometric knowledge whereas supporting recognition (it is conjointly called secure biometric recognition). However, the biometric data that are derived from a person sometimes vary slightly due to a variety of reasons, like distortion during picture capture, and it is tough to use traditional techniques, like classical encryption algorithms, in secure biometric recognition. The negative database (NDB) is a new technique for privacy preservation. Reversing the NDB has been demonstrated to be an NP-laborious drawback, and many algorithms for generating laborious-to-reverse NDBs are proposed. In this Project, initial, we tend to propose negative iris recognition, that could be a novel secure iris recognition theme that is based mostly on the NDB. We have a tendency to show that negative iris recognition supports several important methods in iris recognition, e.g., shifting and masking. Next, we analyze the protection and efficiency of negative iris recognition. Experimental results show that negative iris recognition is an effective and secure iris recognition scheme. Specifically, negative iris recognition will achieve a highly promising recognition performance (i.e., GAR = 98.94percent at FAR = zero.01%, EER = 0.sixtypercent) on the standard database CASIA-IrisV3-Interval.