Deep Representation-Based Feature Extraction and Recovering for Finger-Vein Verification

Qin, Huafeng; Yacoubi, Mounîm El

doi:10.1109/tifs.2017.2689724

Cited by 183 publications

(131 citation statements)

References 38 publications

Supporting

Mentioning

127

Contrasting

Order By: Relevance

“…In contrast to this, the proposed method straightly trains its output to be a compact 128-D embedding using a triplet loss function. A lower value of EER i.e., 0.66% has been achieved on PolyU palm vein, which is superior to the EER values [11,7,12]. In addition, an EER of 3.71% is achieved on the most challenging CASIA dataset which is extremely better than the similar works done in.…”

Section: Experiment-3mentioning

confidence: 65%

PVSNet: Palm Vein Authentication Siamese Network Trained using Triplet Loss and Adaptive Hard Mining by Learning Enforced Domain Specific Features

Thapar

Jaswal

Nigam

et al. 2019

2019 IEEE 5th International Conference on Identity, Security, and Behavior Analysis (ISBA)

View full text Add to dashboard Cite

Designing an end-to-end deep learning network to match the biometric features with limited training samples is an extremely challenging task. To address this problem, we propose a new way to design an end-to-end deep CNN framework i.e., PVSNet that works in two major steps: first, an encoder-decoder network is used to learn generative domain-specific features followed by a Siamese network in which convolutional layers are pre-trained in an unsupervised fashion as an autoencoder. The proposed model is trained via triplet loss function that is adjusted for learning feature embeddings in a way that minimizes the distance between embedding-pairs from the same subject and maximizes the distance with those from different subjects, with a margin. In particular, a triplet Siamese matching network using an adaptive margin based hard negative mining has been suggested. The hyper-parameters associated with the training strategy, like the adaptive margin, have been tuned to make the learning more effective on biometric datasets. In extensive experimentation, the proposed network outperforms most of the existing deep learning solutions on three type of typical vein datasets which clearly demonstrates the effectiveness of our proposed method.

show abstract

Section: Experiment-3mentioning

confidence: 65%

PVSNet: Palm Vein Authentication Siamese Network Trained using Triplet Loss and Adaptive Hard Mining by Learning Enforced Domain Specific Features

Thapar

Jaswal

Nigam

et al. 2019

2019 IEEE 5th International Conference on Identity, Security, and Behavior Analysis (ISBA)

View full text Add to dashboard Cite

show abstract

“…Biometric verification systems like iris [125,65], fingerprint [94], finger vein [170], dental records [93], involve segmentation of various informative regions for efficient analysis.…”

Section: Forensicsmentioning

confidence: 99%

Understanding Deep Learning Techniques for Image Segmentation

et al. 2019

View full text Add to dashboard Cite

The machine learning community has been overwhelmed by a plethora of deep learning based approaches. Many challenging computer vision tasks such as detection, localization, recognition and segmentation of objects in unconstrained environment are being efficiently addressed by various types of deep neural networks like convolutional neural networks, recurrent networks, adversarial networks, autoencoders and so on. While there have been plenty of analytical studies regarding the object detection or recognition domain, many new deep learning techniques have surfaced with respect to image segmentation techniques. This paper approaches these various deep learning techniques of image segmentation from an analytical perspective. The main goal of this work is to provide an intuitive understanding of the major techniques that has made significant contribution to the image segmentation domain. Starting from some of the traditional image segmentation approaches, the paper progresses describing the effect deep learning had on the image segmentation domain. Thereafter, most of the major segmentation algorithms have been logically categorized with paragraphs dedicated to their unique contribution. With an ample amount of intuitive explanations, the reader is expected to have an improved ability to visualize the internal dynamics of these processes.

show abstract

“…Hyung et al [17] present an effective finger vein verification system based on VGG-16, which achieves excellent results in realistic databases. Qin et al [6] design a 5-layers CNN model for finger vein feature extraction and construct a fully convolutional network to recover pattern maps; their experimental results illustrate that the recovered pattern maps can be powerful in finger vein feature representation.…”

Section: A Finger Vein Verification and Related Workmentioning

confidence: 99%

“…3) The fully convolutional network (FCN) [18] is used as the basic architecture of the FV-GAN framework. Compared with other CNN-based methods such as DeepVein [17] and CNN+FCN [6] for vein pattern extraction, FV-GAN can predict binary vein patterns from vein images of any size in one forward propagation and transform a vein image into a pattern map directly without post-processing. The vein pattern extraction of our FV-GAN is time-saving, which enhances the practicality of finger vein verification.…”

Section: B Gans and Our Contributionsmentioning

confidence: 99%

See 1 more Smart Citation

FV-GAN: Finger Vein Representation Using Generative Adversarial Networks

Yang

Hui

Chen

et al. 2019

IEEE Trans.Inform.Forensic Secur.

105

View full text Add to dashboard Cite

In finger vein verification, the most important and challenging part is to robustly extract finger vein patterns from low-contrast infrared finger images with limited a priori knowledge. Although recent convolutional neural network (CNN)-based methods for finger vein verification have shown powerful capacity for feature representation and promising perspective in this area, they still have two critical issues to address. First, these CNNbased methods unexceptionally utilize fully connected layers, which restricts the size of finger vein images to process and increases the processing time. Second, the capacity of CNN for feature representation generally suffers from the low quality of finger vein ground-truth pattern maps for training, particularly due to outliers and vessel breaks. To address these issues, in this paper we propose a novel approach termed FV-GAN to finger vein extraction and verification, based on generative adversarial network (GAN), as the first attempt in this area. Unlike the CNN-based methods, FV-GAN learns from the joint distribution of finger vein images and pattern maps rather than the direct mapping between them, with the aim at achieving stronger robustness against outliers and vessel breaks. Moreover, FV-GAN adopts fully convolutional networks as the basic architecture, and discards fully connected layers, which relaxes the constraint on the input image size and reduces the computational expenditure for feature extraction. Furthermore, we design an adversarial training strategy and propose a hybrid loss function for FV-GAN. The experimental results on two public databases show a significant improvement by FV-GAN in finger vein verification in terms of both verification accuracy and equal error rate.Index Terms-Finger vein verification, pattern extraction, convolutional neural network (CNN), generative adversarial network (GAN), cycle-consistent adversarial network (CycleGAN), deep convolutional generative adversarial network (DCGAN), U-Net.

show abstract

Deep Representation-Based Feature Extraction and Recovering for Finger-Vein Verification

Cited by 183 publications

References 38 publications

PVSNet: Palm Vein Authentication Siamese Network Trained using Triplet Loss and Adaptive Hard Mining by Learning Enforced Domain Specific Features

PVSNet: Palm Vein Authentication Siamese Network Trained using Triplet Loss and Adaptive Hard Mining by Learning Enforced Domain Specific Features

Understanding Deep Learning Techniques for Image Segmentation

FV-GAN: Finger Vein Representation Using Generative Adversarial Networks

Contact Info

Product

Resources

About