Nonintrusive Finger-Vein Recognition System Using NIR Image Sensor and Accuracy Analyses According to Various Factors

Pham, Tuyen Danh; Park, Young Ho; Nguyen, Dat Tien; Kwon, Seung Yong; Park, Kang Ryoung

doi:10.3390/s150716866

Cited by 27 publications

(36 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To overcome the limitations of the token-based and knowledge-based methods, biometric-based methods are increasingly being used as an alternative using the information from several physical and/or behavioral characteristics of people as the key (or password) to protect the personal information [ 1 ]. Many biometric features have been used in applications such as fingerprint [ 4 , 5 ], face [ 6 , 7 ], finger-vein [ 8 , 9 , 10 ], palm-vein [ 11 , 12 ] and iris [ 13 , 14 , 15 ]. The use of biometric features offers several advantages over the token-based and knowledge-based methods.…”

Section: Introductionmentioning

confidence: 99%

“…Although the biometric-based methods have proven efficient for authentication with high recognition rate [ 4 , 5 , 6 , 7 , 8 , 9 , 10 , 11 , 12 , 13 , 14 , 15 ], they still have their limitations. There are two main problems with a biometric system: the effect of image capturing condition and the potential for spoofing attacks.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Spoof Detection for Finger-Vein Recognition System Using NIR Camera

Nguyen

Yoon

Pham

et al. 2017

Sensors

View full text Add to dashboard Cite

Finger-vein recognition, a new and advanced biometrics recognition method, is attracting the attention of researchers because of its advantages such as high recognition performance and lesser likelihood of theft and inaccuracies occurring on account of skin condition defects. However, as reported by previous researchers, it is possible to attack a finger-vein recognition system by using presentation attack (fake) finger-vein images. As a result, spoof detection, named as presentation attack detection (PAD), is necessary in such recognition systems. Previous attempts to establish PAD methods primarily focused on designing feature extractors by hand (handcrafted feature extractor) based on the observations of the researchers about the difference between real (live) and presentation attack finger-vein images. Therefore, the detection performance was limited. Recently, the deep learning framework has been successfully applied in computer vision and delivered superior results compared to traditional handcrafted methods on various computer vision applications such as image-based face recognition, gender recognition and image classification. In this paper, we propose a PAD method for near-infrared (NIR) camera-based finger-vein recognition system using convolutional neural network (CNN) to enhance the detection ability of previous handcrafted methods. Using the CNN method, we can derive a more suitable feature extractor for PAD than the other handcrafted methods using a training procedure. We further process the extracted image features to enhance the presentation attack finger-vein image detection ability of the CNN method using principal component analysis method (PCA) for dimensionality reduction of feature space and support vector machine (SVM) for classification. Through extensive experimental results, we confirm that our proposed method is adequate for presentation attack finger-vein image detection and it can deliver superior detection results compared to CNN-based methods and other previous handcrafted methods.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Spoof Detection for Finger-Vein Recognition System Using NIR Camera

Nguyen

Yoon

Pham

et al. 2017

Sensors

View full text Add to dashboard Cite

show abstract

“…Recently, finger vein imaging technology has been under development using the shadow effect of near-infrared light-emitting diodes (NIR LEDs) [6,7,8,9]. This method, however, might degrade the image contrast because LED light is not collimated and resultantly spreads out of the finger, which leads to higher background noise.…”

Section: Introductionmentioning

confidence: 99%

Imaging of the Finger Vein and Blood Flow for Anti-Spoofing Authentication Using a Laser and a MEMS Scanner

Lee

Moon

Lim

et al. 2017

Sensors

View full text Add to dashboard Cite

A new authentication method employing a laser and a scanner is proposed to improve image contrast of the finger vein and to extract blood flow pattern for liveness detection. A micromirror reflects a laser beam and performs a uniform raster scan. Transmissive vein images were obtained, and compared with those of an LED. Blood flow patterns were also obtained based on speckle images in perfusion and occlusion. Curvature ratios of the finger vein and blood flow intensities were found to be nearly constant, regardless of the vein size, which validated the high repeatability of this scheme for identity authentication with anti-spoofing.

show abstract

“…In current age of Information security technology, there is widespread uses of biometric technologies such as fingerprint, veins, face, voice, and face recognition in various access control, automatic teller machines (ATMs), financial transactions and forensics [1]. Biometric finger vein verification has been proved to be the best as it can solve many shortcomings of other biometric technologies, such drawbacks like fingerprint sweat effect, scars and distortions; face recognition illumination and pose change.…”

Section: Introductionmentioning

confidence: 99%

A Novel Approach for Finger Vein Pattern Enhancement using Gabor and Canny Edge Detector

Akintoye¹,

Shafry²,

Abdullah³

2017

IJCA

View full text Add to dashboard Cite

Biometrics is the science of identifying a person using physiological or behavioural features. A biometric verification system authenticates an individual's identity by matching the live biometric template to his/her biometric template or templates stored in the system database. Nevertheless, finger vein verification system is cost effective in comparison but high in accuracy with opportunities of fake detection and biocryptography system. Previous research on finger vein verification has proved that it's accuracy relies on enhancement of vein image pattern quality. However, at times noise generates as a result of hair and skin texture, which is as well enhanced because they are much resembles the vein structure. Noise is any process that affects the original image since it is not part of the original image. This causes great error when extracting accurate vein patterns. It also leads to increasing processing time during finger vein extraction, which is eventually cause an inaccuracy in matching/verification system. To overcome this problem, a novel approach for finger vein pattern enhancement using Gabor-Canny edge detector is proposed, which is far better and more accurate than previous method.

show abstract

Nonintrusive Finger-Vein Recognition System Using NIR Image Sensor and Accuracy Analyses According to Various Factors

Cited by 27 publications

References 25 publications

Spoof Detection for Finger-Vein Recognition System Using NIR Camera

Spoof Detection for Finger-Vein Recognition System Using NIR Camera

Imaging of the Finger Vein and Blood Flow for Anti-Spoofing Authentication Using a Laser and a MEMS Scanner

A Novel Approach for Finger Vein Pattern Enhancement using Gabor and Canny Edge Detector

Contact Info

Product

Resources

About