scholarly journals A NEW FINGER-VEIN RECOGNITION SYSTEM USING THE COMPLETE LOCAL BINARY PATTERN AND THE PHASE ONLY CORRELATION

2021 ◽  
Vol 7 (1) ◽  
pp. 38-56
Author(s):  
Ahmed A. Mustafa ◽  
Ahmed AK Tahir
Keyword(s):  
Local Binary Pattern ◽  
Recognition System ◽  
Finger Vein ◽  
Vein Recognition ◽  
Finger Vein Recognition

scholarly journals Finger-Vein Recognition Using Heterogeneous Databases by Domain Adaption Based on a Cycle-Consistent Adversarial Network

Sensors ◽  
2021 ◽  
Vol 21 (2) ◽  
pp. 524
Author(s):  
Kyoung Jun Noh ◽  
Jiho Choi ◽  
Jin Seong Hong ◽  
Kang Ryoung Park
Keyword(s):  
Domain Adaptation ◽  
Recognition Accuracy ◽  
Recognition System ◽  
Heterogeneous Databases ◽  
Second Best ◽  
Finger Vein ◽  
Adversarial Network ◽  
Image Characteristics ◽  
Vein Recognition ◽  
Finger Vein Recognition

The conventional finger-vein recognition system is trained using one type of database and entails the serious problem of performance degradation when tested with different types of databases. This degradation is caused by changes in image characteristics due to variable factors such as position of camera, finger, and lighting. Therefore, each database has varying characteristics despite the same finger-vein modality. However, previous researches on improving the recognition accuracy of unobserved or heterogeneous databases is lacking. To overcome this problem, we propose a method to improve the finger-vein recognition accuracy using domain adaptation between heterogeneous databases using cycle-consistent adversarial networks (CycleGAN), which enhances the recognition accuracy of unobserved data. The experiments were performed with two open databases—Shandong University homologous multi-modal traits finger-vein database (SDUMLA-HMT-DB) and Hong Kong Polytech University finger-image database (HKPolyU-DB). They showed that the equal error rate (EER) of finger-vein recognition was 0.85% in case of training with SDUMLA-HMT-DB and testing with HKPolyU-DB, which had an improvement of 33.1% compared to the second best method. The EER was 3.4% in case of training with HKPolyU-DB and testing with SDUMLA-HMT-DB, which also had an improvement of 4.8% compared to the second best method.

An Arcloss-Based and Openset-Test-Oriented Finger Vein Recognition System

2021 ◽  
pp. 287-294
Author(s):  
Zhenxiang Chen ◽  
Wangwang Yu ◽  
Haohan Bai ◽  
Yongjie Li
Keyword(s):  
Recognition System ◽  
Finger Vein ◽  
Vein Recognition ◽  
Finger Vein Recognition

Near Infrared Finger Vein Recognition Method Based on Subspace Projection Technology

2014 ◽  
Vol 1030-1032 ◽  
pp. 2382-2385 ◽  
Author(s):  
Lin Lin Fan ◽  
Hui Ma ◽  
Ke Jun Wang ◽  
Yong Liang Shen ◽  
Ying Shi ◽  
...  
Keyword(s):  
Near Infrared ◽  
Nearest Neighbor ◽  
Recognition Performance ◽  
Recognition System ◽  
Critical Issue ◽  
Subspace Projection ◽  
Threshold Method ◽  
Finger Vein ◽  
Vein Recognition ◽  
Finger Vein Recognition

Finger vein recognition refers to a recent biometric technique which exploits the vein patterns in the human finger to identify individuals. Finger vein recognition faces a number of challenges. One critical issue is the performance of finger vein recognition system. To overcome this problem, a finger vein recognition algorithm based on one kind of subspace projection technology is presented. Firstly, we use Kapur entropy threshold method to achieve the purpose of intercepting region of finger under contactless mode. Then the finger vein features were extracted by 2DPCA method. Finally, we used of nearest neighbor distance classifier for matching. The results indicate that the algorithm has good recognition performance.

Real-Time Finger-Vein Recognition for Security and Monitoring System

2014 ◽  
Vol 550 ◽  
pp. 194-203
Author(s):  
S. Nandhini ◽  
D. Shyam
Keyword(s):  
Private Information ◽  
Electronic Devices ◽  
Recognition System ◽  
Biometric Authentication ◽  
Finger Vein ◽  
Security Authentication ◽  
Consumer Electronic ◽  
Authentication System ◽  
Vein Recognition ◽  
Finger Vein Recognition

— The demand for simple, convenient and high security authentication systems protecting private information is rising with the development of improved consumer electronic devices. In existing systems cards, pin numbers and passwords are used for authentication. However theft of cards and guessing of pin numbers and passwords by exploiters is a serial threat. Hence the need to protect private information by means of biometric solutions is very essential. The proposed system finger vein recognition system is a biometric authentication system. The maximum curvature method of feature extraction used here extracts the centrelines without being affected by fluctuations in vein width and brightness. The results of processing are sent using GSM to owners or administrators. The system can be used for application such as bank ATM identification and verification, automatic door locking control systems and automated attendance register system.

Pengenalan Finger Vein Menggunakan Local Line Binary Pattern dan Learning Vector Quantization

2018 ◽  
Vol 9 (2) ◽  
pp. 52-57
Author(s):  
Jayanti Yusmah Sari ◽  
Rizal Adi Saputra
Keyword(s):  
Feature Extraction ◽  
Vector Quantization ◽  
Recognition System ◽  
Learning Vector Quantization ◽  
Feature Extraction Method ◽  
Finger Vein ◽  
Straight Line ◽  
Vein Recognition ◽  
Form Features ◽  
Finger Vein Recognition

This research proposes finger vein recognition system using Local Line Binary Pattern (LLBP) method and Learning Vector Quantization (LVQ). LLBP is is the advanced feature extraction method of Local Binary Pattern (LBP) method that uses a combination of binary values from neighborhood pixels to form features of an image. The straight-line shape of LLBP can extract robust features from the images with unclear veins, it is more suitable to capture the pattern of vein in finger vein image. At the recognition stage, LVQ is used as a classification method to improve recognition accuracy, which has been shown in earlier studies to show better results than other classifier methods. The three main stages in this research are preprocessing, feature extraction using LLBP method and recognition using LVQ. The proposed methodology has been tested on the SDUMLA-HMT finger vein image database from Shandong University. The experiment shows that the proposed methodology can achieve accuracy up to 90%. Index Terms—finger vein recognition, Learning Vector Quantization, LLBP, Local Line Binary Pattern, LVQ.

Sign in / Sign up

Export Citation Format

Share Document