Finger-based personal authentication: a comparison of feature-extraction methods based on principal component analysis, most discriminant features and regularised-direct linear discriminant analysis

Pavešić, Nikola; Ribarić, Slobodan; Grad, Benjamin

doi:10.1049/iet-spr.2008.0149

Cited by 10 publications

(24 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The same indoor environment has been used with a black background to collect image data [15]. To evaluate our proposed method in extracting the ROIs from the four finger images, we compared our method with [10] [7] and [2] to build up the comparisons. These publications use only a small ROI region.…”

Section: Results Comparisons and Discussionmentioning

confidence: 99%

“…Furthermore, a low cost multi-modal identification system was proposed in [11] by using FT print, palm and hand geometry. A comparison study for a fingerprint and FT surface was given in [7] based on regularized-direct linear discriminant analysis, various discriminant features and principal component analysis. A combination of knuckle print and the palm print was described in [9] as a verification system.…”

Section: Prior Workmentioning

confidence: 99%

“…A multiplication operation has been used to combine the original grayscale hand image with the binary image. Eight connected contour tracing, which described in [7], was applied to draw the boundaries. The main finger points (tips and valleys) can be specified from the local minima and local maxima points.…”

Section: A Finger Extractions/roimentioning

confidence: 99%

“…One of the most popular biometrics is the human hand. It consists of rich characteristics, which can be used as reliable features to recognize people such as three-dimensional hand geometry, two-dimensional hand geometry, finger geometry, palm print [2], outer finger knuckles [3] [4], palm veins [5], finger veins [6] and fingerprint [7]. However, some of these features are challenging due to obstacles as palm veins and finger veins require a special capturing device with a specific environment.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Human authentication with finger textures based on image feature enhancement

Al-Nima

Dlay

Woo

et al. 2015

2nd IET International Conference on Intelligent Signal Processing 2015 (ISP)

View full text Add to dashboard Cite

The main goal of this paper is to authenticate people according to their finger textures. We propose to extract Finger Texture (FT) features of the four finger images (index, middle, ring and little) from a low resolution contactless hand image. Furthermore, we apply a new Image Feature Enhancement (IFE) method to enhance the FTs. The resulting feature image is segmented and a Probabilistic Neural Network (PNN) is employed as an intelligent classifier for recognition. Experimental results illustrate that the proposed approach has superior performance than recent published work. Moreover, the best IFE results were obtained with the Equal Error Rate (EER) equal to 4.07%.

show abstract

Section: Results Comparisons and Discussionmentioning

confidence: 99%

Section: Prior Workmentioning

confidence: 99%

Section: A Finger Extractions/roimentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Human authentication with finger textures based on image feature enhancement

Al-Nima

Dlay

Woo

et al. 2015

2nd IET International Conference on Intelligent Signal Processing 2015 (ISP)

View full text Add to dashboard Cite

show abstract

“…The eigen values of the finger and palm were employed as types of feature extraction. In 2009, Pavesic et al [23] proposed a human authentication system based on the fusion between the FTs and fingerprints of four fingers. In this study, the authors provide comparisons of three feature extraction methods.…”

Section: Literature Reviewmentioning

confidence: 99%

Finger Texture Verification Systems Based on multiple spectrum Lighting Sensors with Four Fusion Levels

Al-Kaltakchi

Omar

Abdullah

et al. 2019

Iraqi Journal of ICT

View full text Add to dashboard Cite

Finger Texture (FT) is one of the most recent attractive biometric characteristic. Itrefers to a finger skin area which is restricted between the fingerprint and the palm print (just after including the lower knuckle). Different specifications for the FT can be obtained by employing multiple images spectrum of lights. This inspired the insight of applying a combination between the FT features that acquired by utilizing two various spectrum lightings in order to attain high personal recognitions. Four types of fusion will be listed and explained here: Sensor Level Fusion (SLF), Feature Level Fusion (FLF), Score Level Fusion (ScLF) and Decision Level Fusion (DLF). Each fusion method is employed and examined for an FT verification system. From the database of Multiple Spectrum CASIA (MSCASIA), FT images have been collected. Two types of spectrum lights have been exploited (the wavelength of 460 nm, which represents a Blue (BLU) light, and the White (WHT) light). Supporting comparisons were performed, including the state-of-the-art. Best recognition performance were recorded for the FLF based concatenation rule by improving the Equal Error Rate (EER) percentages from 5% for the BLU and 7% for the WHT to 2%.

show abstract