home  |   research   |  members   |  projects  |  publications   |  conferences of interest   |  downloads   |  contact  |  intern
 
 

Finger Vein Feature Level Fusion Framework

This is "The Multimedia Signal Processing and Security Lab", short WaveLab, website. We are a research group at the Computer Sciences Department of the University of Salzburg headed by Andreas Uhl. The short name "WaveLab" already indicates that wavelets are among our favorite tools - we have 15 years of experience in this area. Our research is focused on Multimedia Security including Watermarking, Image and Video Compression, Medical Image Classification, and Biometrics.

Information

This is a feature level fusion framework for finger vein recognition implemented in MATLAB. It was tested on MATLAB 2013b and should work with all version of MATLAB newer or equal to 2013b. This software is under the Simplified BSD license.

The framework contains all the feature extraction and fusion methods used for the experiments in the paper

Christof Kauba, Emanuela Piciucco, Emanuele Maiorana, Patrizio Campisi, and Andreas Uhl “Advanced Variants of Feature Level Fusion for Finger Vein Recognition”, in Proceedings of the International Conference of the Biometrics Special Interest Group, 2016.

Feature Extraction Methods

The following 6 feature extractors, all outputting binary vein images, are contained:

  • Maximum Curvature
  • Repeated Line Tracking
  • Wide Line Detector
  • Principal Curvature
  • Gabor Filter
  • IUWT

Fusion Methods

There are two different types of fusion:

  • Single feature extractor only: Fusing the outputs of a single feature extractor while varying its parameters
  • Multiple feature extractors: Fusing the outputs of (all) different feature extractors

The following fusion schemes were tested and are contained in the framework:

  • Majority Voting
  • Weighted Average
  • STAPLE
  • STAPLER
  • COLLATE

Package Information

The main directory contains the setup and the main functions for the two different types of fusion, including the matching/score calculation function. The package further contains the following subdirectories:

  • data: Here the UTFVP images should be placed and all the feature, score and results files can be found
  • functions_eer_evaluation: Functions from the Biosecure Tool to determine EER and ROC curves (modified)
  • functions_feature_extraction: Implementations of the different feature extractors
  • functions_fusion: Implementations of the fusion methods (MV, Av and wrapper for STAPLE/STAPLER/COLLATE)
  • functions_ton: Functions from B.T. Ton for feature extractors and matching
  • iuwt_vessels_lib: Path where the ARIA Vessels Lib should be put into
  • masi-fusion: Path where the MASI Fusion framework should be placed
  • utility_functions: Some utility functions, e.g. a progress bar class

Usage Instructions

The whole framework is written in MATLAB. For more detailed usage instructions have a look at the readme.txt file contained in the package. It depends on the following external software packages, which have to be downloaded seperately:

External Dependencies

  • MASI Fusion: Implements the STAPLE / STAPLER and COLLATE fusion algorithms. The MATLAB version is available at NITRC
  • ARIA Vessel Library: A MATLAB implementation is freely available at Sourceforge

Dataset

The UTFVP finger vascular pattern dataset has been utilized which need to be obtained from the University of Twente and should be put into the TODO directory.

Other Dependencies

The following methods have not been implemented by ourselves but are already included in the framework sources:

For the Maximum Curvature, Repeated Line Tracking, Wide Line Detector and Principal Curvature feature extraction as well as for the finger boundary detection and the finger normalisation an implementation of B.T. Ton was utilised which is publicly availabale through MATLAB Central. The Gabor Filter approach is a custom implementation of the approach by Kumar et al. [6] done by Emanuela Piciucco in [7], which is also included in the fusion framework package.

For matching an implementation of B.T. Ton of the method proposed by Miura et al. [2, 3] which can also be downloaded via MATLAB Central was used.

For the EER determination the routine of the Biosecure Tool was utilisied which can be found here.

For adaptive thresholding an implementation by Guanglei Xiong, which freely available at MATLAB Central was used.

For Gaussian filtering an implementation by F. van der Heijden, freely available at MATLAB Central was used.

References

  • UTFVP Dataset
  • [1] B.T. Ton, R.N.J. Veldhuis. A high quality finger vascular pattern dataset collected using a custom designed capturing device. International Conference on Biometrics, ICB 2013, 2013. URL http://doc.utwente.nl/87790/.
  • Maximum Curvature
  • [2] Naoto Miura, Akio Nagasaka, Takafumi Miyatake. Extraction of finger-vein patterns using maximum curvature points in image profiles. IEICE transactions on information and systems, 90(8):1185—1194, 2007
  • Repeated Line Tracking
  • [3] Naoto Miura, Akio Nagasaka, Takafumi Miyatake. Feature extraction of finger-vein patterns based on repeated line tracking and its application to personal identification. Machine Vision and Applications, 15(4):194—203, 2004
  • Wide Line Detector
  • [4] Beining Huang, Yanggang Dai, Rongfeng Li, Darun Tang, Wenxin Li. Finger-vein authentication based on wide line detector and pattern normalization. Pattern Recognition (ICPR), 2010 20th International Conference on:1269—1272, 2010
  • Principal Curvature
  • [5] Joon Hwan Choi, Wonseok Song, Taejeong Kim, Seung-Rae Lee, Hee Chan Kim. Finger vein extraction using gradient normalization and principal curvature. IS&T/SPIE Electronic Imaging:725111—725111, 2009
  • Gabor Filter
  • [6] Ajay Kumar, Yingbo Zhou. Human identification using finger images. Image Processing, IEEE Transactions on, 21(4):2228—2244, 2012

    [7] E. Piciucco, E. Maiorana, C. Kauba, A. Uhl, P. Campisi. Cancelable Biometrics for Finger Vein Recognition. 2016 International Workshop on Sensing, Processing and Learning for Intelligent Machines (SPLINE), 2016.

  • IUWT
  • [8] Jean-Luc Starck, Jalal Fadili, Fionn Murtagh. The Undecimated Wavelet Decomposition and its Reconstruction. IEEE Transactions on Image Processing, 16(2):297—309, 2007. URL http://dx.doi.org/10.1109/TIP.2006.887733
  • STAPLE
  • [9] Simon K Warfield, Kelly H Zou, William M Wells. Simultaneous truth and performance level estimation (STAPLE): an algorithm for the validation of image segmentation. Medical Imaging, IEEE Transactions on, 23(7):903—921, 2004
  • STAPLER
  • [10] Bennett A Landman, Andrew J Asman, Andrew G Scoggins, John A Bogovic, Fangxu Xing, Jerry L Prince. Robust statistical fusion of image labels. Medical Imaging, IEEE Transactions on, 31(2):512—522, 2012
  • COLLATE
  • [11] Andrew J Asman, Bennett A Landman. Robust statistical label fusion through consensus level, labeler accuracy, and truth estimation (COLLATE). Medical Imaging, IEEE Transactions on, 30(10):1779—1794, 2011

Contact

Sources and Executables

The code is available upon request.

Please fill out this form to request a download link for the software:

Name:
Affiliation:
Email address: