Detecting Iris Liveness with Batch Normalized Convolutional Neural Network

Abstract

Aim to countermeasure the presentation attack for iris recognition system, an iris liveness detection scheme based on batch normalized convolutional neural network (BNCNN) is proposed to improve the reliability of the iris authentication system. The BNCNN architecture with eighteen layers is constructed to detect the genuine iris and fake iris, including convolutional layer, batch-normalized (BN) layer, Relu layer, pooling layer and full connected layer. The iris image is first preprocessed by iris segmentation and is normalized to 256×256 pixels, and then the iris features are extracted by BNCNN. With these features, the genuine iris and fake iris are determined by the decision-making layer. Batch normalization technique is used in BNCNN to avoid the problem of over fitting and gradient disappearing during training. Extensive experiments are conducted on three classical databases: the CASIA Iris Lamp database, the CASIA Iris Syn database and Ndcontact database. The results show that the proposed method can effectively extract micro texture features of the iris, and achieve higher detection accuracy compared with some typical iris liveness detection methods.

Hyperspectral Image Super-Resolution via Adaptive Dictionary Learning and Double ℓ 1 Constraint

“…In the future, we can combine the tensor model [54] and the shape-adaptive technique [55,56] to explore the spatial-spectral information adaptively and sufficiently. Deep-learning approaches have recently gained great attention in many fields [57][58][59][60][61][62][63][64]. It will be a new task to design a deep architecture to improve the performance of the HSI SR.…”

A Novel Cubic Convolutional Neural Network for Hyperspectral Image Classification

“…DL can capture the details of real data and achieve the best balance between discernibility and robustness. In order to fully demonstrate the advantages of the CNN, we adopt a 3D convolutional layer for feature capture and a batch normalization (BN) layer is added after the convolutional layer [44]. BN normalizes the data after convolution, eliminating the effect of zoom in and zoom out caused by w and solving the problem of gradient disappearance and explosion.…”

Unsteady State Lightweight Iris Certification Based on Multi-Algorithm Parallel Integration

“…As a common deep learning architecture, convolutional neural network is commonly used in various biometric recognitions, such as face recognition [54], palmprint recognition [55], fingerprint recognition [56], and iris recognition [57]. The feature cognition of the traditional convolutional neural network is to express the iris category by setting the label.…”