An approach for iris contact lens detection and classification using ensemble of customized DenseNet and SVM

In spite of the prominent advancements in iris recognition, it can significantly be deceived by contact lenses. As the contact lens wraps the iris region and obstructs sensors from capturing the actual iris. Moreover, cosmetic lenses are prone to forge the iris recognition system by registering an individual with fake iris signatures. Therefore, it is foremost to perceive the existence of the contact lens in human eyes prior to access an iris recognition system. This paper introduces a novel Densely Connected Contact Lens Detection Network (DCLNet) has been proposed, which is a deep convolutional network with dense connections among layers. DCLNet has been designed through a series of customizations over Densenet121 with the addition of Support Vector Machine (SVM) classifier on top. It accepts raw iris images without segmentation and normalization, nevertheless the impact of iris normalization on the proposed model’s performance is separately analyzed. Further, in order to assess the proposed model, extensive experiments are simulated on two widely eminent databases (Notre Dame (ND) Contact Lens 2013 Database and IIIT-Delhi (IIITD) Contact Lens Database). Experimental results reaffirm that the proposed model improves the Correct Classification Rate (CCR) up to 4% as compared to the state of the arts.