Identification from the iris of the eye with deep neural network

Iris detection is very accurate compared to many other biometric features. Iris recognition has been an active research area during last few decades, because of its wide applications in security, from airports to homeland security border control. Recently, deep learning approaches, especially convolutional neural networks (CNNs), have attracted extensive attention in iris recognition. popular architectures such as convolution neural network (CNN), Restricted Boltzmann Machines (RBM), the encoder automatically (AN) and sparse coding for the identification based on iris images using deep learning to do. Deep learning is, in fact, a new attitude to the idea of neural networks with a long history, which resurfaces in a new format every few years. The convolutional neural network has a precision of ۱۰۰ on training data, neural convolutional network has a higher accuracy than other methods of deep learning. The recognition system implement using the MATLAB software package.

کلیدواژه ها:

Iris ، Convolutional Neural Networks (CNN) ، Limited Boltzmann Machine (RBM) ، Autoencoder (AN) ، Sparse Coding