Fingerprint Liveness Detection Using an Improved CNN With Image Scale Equalization

Abstract

Due to the lack of pre-judgment of fingerprints, fingerprint authentication systems are frequently vulnerable to artificial replicas. Anonymous people can impersonate authorized users to complete various authentication operations, thereby disrupting the order of life and causing tremendous economic losses to society. Therefore, to ensure that authorized users' fingerprint information is not used illegally, one possible anti-spoofing technique, called fingerprint liveness detection (FLD), has been exploited. Compared with the hand-crafted feature methods, the deep convolutional neural network (DCNN) can automatically learn the high-level semantic detail via supervised learning algorithm without any professional background knowledge. However, one disadvantage of most CNNs models is that fixed scale images (e.g., 227 × 227) are essential in the input layer. Although the scale problem can be handled by cropping or scaling operations via transforming an image of any scale into a fixed scale, they can easily cause some key texture information loss and image resolution degradation, which will weaken the generalization performance of the classifier model. In this paper, a novel FLD method called an improved DCNN with image scale equalization, has been proposed to preserve texture information and maintain image resolution. Besides, an adaptive learning rate method has been used in this paper. In the performance evaluation, the confusion matrix is applied into FLD for the first time as a performance indicator. The amounts of the experimental results based on the LivDet 2011 and LivDet 2013 data sets also verify that the detection performance of our method is superior to other methods.

Densely Connected Convolutional Network Optimized by Genetic Algorithm for Fingerprint Liveness Detection

“…In order to demonstrate the efficiency of our approach, we compare the performance on different sub-datasets of proposed model DenseNet-BC-64(k=20) with other state-ofthe-art works, such as autoencoder [42], ResNet [43], [44], DenseNet [7], deep belief network [45], conventional CNN [46], [47] and transfer learning models (VGG and Alexnet [22]). The ACE on LivDet testing set of different models is recorded in Table 7.…”

“…Nogueira et al (2016) [22] designed a CNN-Random model as the classifier with preprocessed images as input. Similar methods used CNN as a classifier with preprocessed images [23] or image patches [24] as input. Some works combined CNN with local descriptors [25], [26] to improve the classification performance.…”

Hierarchical Multimodal Fusion for Ground-Based Cloud Classification in Weather Station Networks

“…Recently, CNN [17]- [20] achieves remarkable performance in many research fields, and meanwhile it is also applied to the ground-based cloud classification. Shi et al [3] presented the Deep Convolutional Activations-based Features (DCAFs) to extract the local texture information from the shallow convolutional layers for ground-based cloud classification.…”

Multi-View Convolutional Neural Networks for Mammographic Image Classification

“…Chougrad et al [21] augmented a mammographic image dataset by randomly transforming and rotating the samples. The CNN exhibits strong performance in the automatic feature extraction from images [22]- [24]. However, training the model on a large-scale image dataset is necessary for making full use of the advantages of the CNN.…”