Iris Discrimination Combined with the Shape and Orientation Recognition

We previously proposed a iris recognition system by a rotation spreading neural network (R-SAN net). The R-SAN net is suitable for orientation recognition of a concentric circular pattern such as iris image. The recognition characteristics of the R-SAN net for both learned and unlearned iris images were investigated. The RS-SAN net had fairly good orientation recognition characteristics only for learned irises, but not for unlearned irises. The recognized orientation for unlearned irises were heavily dispersed from the orientation of input iris although the orientation for learned irises were concentrated around learned orientation. By using the unique characteristics of orientation recognition, new recognition method with the imposter extraction using recognized orientation was developed. The experimental result of new recognition method indicated the false acceptance rate drastically decreased. The equal error rates obtained by the previous and proposed methods were 2.02% and 0.79%, respectively. The imposter rejection method using recognized orientation provided the effective improvement of iris recognition performance.