FPGA-based finger vein biometric system with adaptive illumination for better image acquisition

Lee, Y. H.; Khalil-Hani, Mohamed; Bakhteri, Rabia

doi:10.1109/iscaie.2012.6482079

Cited by 10 publications

(6 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Xu et al [4] and Lee et al [5] proposed adaptive illumination control based on image quality assessment. The quality of the captured vein image is assessed using two-dimensional entropy and the light intensity is adjusted based on the assessment result.…”

Section: Vein Capture Light Source Control Methodsmentioning

confidence: 99%

Review on Vein Enhancement Methods for Biometric System

Yusoff¹

2015

IJRET

View full text Add to dashboard Cite

Vein biometric system uses vein inside human body as a unique identification. Researchers have concluded that human vein pattern is unique to an individual. Vein pattern cannot be stolen or duplicated because it is in the human body. At present, vein pattern in finger, palm, palm-dorsa and wrist of human are used for biometric system. This paper presents a review on vein enhancement methods. This paper begins with overview of vein detection and the advantages of vein as biometric modal. Next, the vein capturing technology to obtain the vein pattern in human body is presented. Finally, preceding works related to vein enhancement methods are discussed and reviewed

show abstract

Section: Vein Capture Light Source Control Methodsmentioning

confidence: 99%

Review on Vein Enhancement Methods for Biometric System

Yusoff¹

2015

IJRET

View full text Add to dashboard Cite

show abstract

“…The image acquisition part of the design is not discussed as it is out of the scope of this paper. For development and testing, the finger-vein image database used in this work was developed in our own laboratory and has been reported in [16]. We describe this image database in more detail in Section 4.1.…”

Section: The Proposed Approachmentioning

confidence: 99%

Finger-vein biometric identification using convolutional neural network

Radzi¹,

Khalil-Hani²,

Bakhteri³

2016

Turk J Elec Eng & Comp Sci

Self Cite

129

View full text Add to dashboard Cite

Abstract:A novel approach using a convolutional neural network (CNN) for finger-vein biometric identification is presented in this paper. Unlike existing biometric techniques such as fingerprint and face, vein patterns are inside the body, making them virtually impossible to replicate. This also makes finger-vein biometrics a more secure alternative without being susceptible to forgery, damage, or change with time. In conventional finger-vein recognition methods, complex image processing is required to remove noise and extract and enhance the features before the image classification can be performed in order to achieve high performance accuracy. In this regard, a significant advantage of the CNN over conventional approaches is its ability to simultaneously extract features, reduce data dimensionality, and classify in one network structure. In addition, the method requires only minimal image preprocessing since the CNN is robust to noise and small misalignments of the acquired images. In this paper, a reduced-complexity four-layer CNN with fused convolutional-subsampling architecture is proposed for finger-vein recognition. For network training, we have modified and applied the stochastic diagonal Levenberg-Marquardt algorithm, which results in a faster convergence time. The proposed CNN is tested on a finger-vein database developed in-house that contains 50 subjects with 10 samples from each finger. An identification rate of 100.00% is achieved, with an 80/20 percent ratio for separation of training and test samples, respectively. An additional number of subjects have also been tested, in which for 81 subjects an accuracy of 99.38% is achieved.

show abstract

“…Conclusions and some future work are discussed in section 6. There were many unimodal vein image acquisition systems, for example, for hand [26] and for finger [9]. However, as far as we are concerned, there is no device to capture a single image blending both finger vein and finger dorsal texture, such as Fig.…”

Section: Introductionmentioning

confidence: 99%

“…In Eq. (8) and Eq (9),. N(k) represents the number of nonzero elements of map k, and φ(B, B ) is the matched bit number of nonzero elements in the binary coded maps B and B .…”

mentioning

confidence: 99%

A hybrid finger identification pattern using Polarized depth-Weighted Binary Direction Coding

Yang

Xue

et al. 2019

Neurocomputing

View full text Add to dashboard Cite

Finger identification is increasingly popular in recent years. In this paper, we propose a new finger identification system to acquire a hybrid pattern of dorsal finger vein and texture in a single image by using only one camera. It effectively reduces the cost and volume of the imaging device to acquire multi-modal patterns. The hybrid pattern of dorsal finger vein and texture is both storage-saving and calculation-saving. As there was no existing method specially developed for this kind of pattern, we propose a new feature extraction method called "Polarized depth-Weighted Binary Direction Coding" (PWBDC). We also establish a new database of such hybrid images of 210 finger samples. Experimental results demonstrate that the proposed system and feature are not only storage and calculation saving, but more importantly effective for identification. The proposed PWBDC method performs well on both the newly established database of hybrid images and a popular public database of traditional finger vein images, superior to many established and state-of-the-art methods.

show abstract

FPGA-based finger vein biometric system with adaptive illumination for better image acquisition

Cited by 10 publications

References 12 publications

Review on Vein Enhancement Methods for Biometric System

Review on Vein Enhancement Methods for Biometric System

Finger-vein biometric identification using convolutional neural network

A hybrid finger identification pattern using Polarized depth-Weighted Binary Direction Coding

Contact Info

Product

Resources

About