Human Identity Verification From Biometric Dorsal Hand Vein Images Using the DL-GAN Method

Alashik, Khaled; Yıldırım, Remzi

doi:10.1109/access.2021.3076756

Cited by 14 publications

(5 citation statements)

References 98 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Alashik et al [4] have posited the DL-GAN method to confirm biometric identity. The DL-GAN approach has the advantage of higher accuracy because it employs a backhand structure for authentication.…”

Section: Related Workmentioning

confidence: 99%

Improved Unsupervised Deep Boltzmann Learning Approach for Accurate Hand Vein Recognition

Nour,

Moustafa,

Abdelhay

et al. 2024

IEEE Access

View full text Add to dashboard Cite

Dorsal hand vein (DHV) recognition is a burgeoning biometric technology that has recently garnered considerable attention. This article uses image processing and deep learning to present a novel DHV recognition approach. It involves detecting and identifying the unique patterns present in the DHV. The proposed system begins with the preprocessing mechanism that is applied to enhance the quality of the acquired images, including contrast enhancement and noise reduction, by using some filters such as Median and Contrast Limited Adaptive Histogram Equalization (CLAHE). Next, a deep learning model, such as a convolutional neural network (CNN), is employed to automatically abstract discriminative features from the preprocessed vein images. The empirical outcomes prove the influence and reliability of the proposed technique for vein recognition, making it a promising solution for biometric authentication systems. Compared with traditional CNN, the proposed approach shows good accuracy and classification rate results. The suggested model achieved a high recognition rate accuracy, recall, precious, and f-score of 99.7%,97%,96%, and 96%, respectively, and a recognition time of about 1283.45 s. To enrich the model's capability for feature recognition and reduce recognition time, decrease the intricacy of learning and the connectivity CNN structure, an alternative approach based on Restricted Boltzmann Machines (RBM) was assessed. This strategy exhibits superior accuracy in comparison to other contemporary algorithms. The proposed RBM achieved a high recognition rate accuracy, recall, precious, and f-score of 99.9%,99%,99%, and 99%, respectively, and a recognition time of about 137.235s.

show abstract

Section: Related Workmentioning

confidence: 99%

Improved Unsupervised Deep Boltzmann Learning Approach for Accurate Hand Vein Recognition

Nour,

Moustafa,

Abdelhay

et al. 2024

IEEE Access

View full text Add to dashboard Cite

show abstract

“…A comparison of different methods for dorsal hand vein image recognition is shown in the study [30] using three performance measures EER, STD (Standard Deviation of Accuracy), and ACC. "Deep learning" (DL) and "generative adversarial networks" (GANs) i.e., DL-GAN method proved to be better as compared to other recognition methods for dorsal hand vein images.…”

Section: Performance Measurementioning

confidence: 99%

Advancements in Biometric Authentication Systems: A Comprehensive Survey on Internal Traits, Multimodal Systems, and Vein Pattern Biometrics

Mane,

Bhosale

2023

RIA

View full text Add to dashboard Cite

Biometric authentication systems, entities that leverage unique biological traits for individual identification, have become increasingly relevant in the digital age, addressing critical safety and security concerns. These biometric identifiers, being distinct and irreversible, uniquely differentiate individuals. Biometric recognition's significance extends to diverse domains, including forensics, defense, surveillance, personal identification, and banking. The impetus for advancements in biometric authentication systems is driven by the imperative need for resilience, high precision, and resistance against spoofing. This paper aims to elucidate the recent advancements in this evolving field. The fundamentals of biometric authentication systems, issues and vulnerabilities inherent in basic biometric systems, as well as the cutting-edge biometric systems developed in recent years, are thoroughly reviewed. The paper further explores how challenges can be mitigated through the deployment of Multimodal biometric systems and vein pattern-based systems. A synopsis of real-time face recognition incorporating morphing attack detection is also provided. This comprehensive survey concludes that the performance of biometric recognition systems is continually being augmented, predominantly through the incorporation of deep learning frameworks and 3D biometric imagery, which offer highly accurate representations of human biometric features.

show abstract

“…Both clockwise and counterclockwise rotations were discernible to us with success.  ALASHIK et al [36] proposed a method based on utilizing Deep learning (DL) and generative adversarial networks (GANs). Deep learning and GAN are combined to create a DL-GAN.…”

Section: Related Workmentioning

confidence: 99%

Dorsal Hand Vein Image Recognition: A Review

A. Rajab1,

M. Hashim2

2023

JEPS

View full text Add to dashboard Cite

Subcutaneous vascularization has become a new solution for identification management over the pastfew years. Systems based on dorsal hand veins are particularly promising for high-security settings. Thedorsal hand vein recognition system comprises the following steps: acquiring images from the databaseand preprocessing them, locating the region of interest, and extracting and recognizing information fromthe dorsal hand vein pattern. This paper reviewed several techniques for obtaining the dorsal hand veinarea and identifying a person. Therefore, this study just provides a comprehensive review of existingprevious theories. This model aims to offer the improvement in the accuracy rate of the system that wasshown in previous studies and to evaluate test samples and training samples for person identificationusing distance criteria or neural networks.

show abstract

Human Identity Verification From Biometric Dorsal Hand Vein Images Using the DL-GAN Method

Cited by 14 publications

References 98 publications

Improved Unsupervised Deep Boltzmann Learning Approach for Accurate Hand Vein Recognition

Improved Unsupervised Deep Boltzmann Learning Approach for Accurate Hand Vein Recognition

Advancements in Biometric Authentication Systems: A Comprehensive Survey on Internal Traits, Multimodal Systems, and Vein Pattern Biometrics

Dorsal Hand Vein Image Recognition: A Review

Contact Info

Product

Resources

About