EEL 851 - Biometrics
Spring 2006
Indian Institute of Technology Delhi, New Delhi

Group Projects

Suggested Topics

(i)  Fingerprint Recognition

(ii) Face Recognition

(iii) Palmprint Recognition

(iv) Hand Geometry Verification

Your group may choose another biometric for the group project (signature verification, iris recognition, speech recognition, etc.). However your decision should be communicated to the instructor on or before 25/02/06.

Schedule

    ·  Phase I: Presentation in Class on the background and the state-of-the-art of the topic of your project during the last week of March (27-30); (worth 10 points of the 10 total)

      ·  Phase II: Presentation and demonstration of your project in Class last week of April (24-28); (worth 30 points of the 40 total) and

      ·  Phase III: Final report (worth 10 points of the 40 total) due on 2nd May to my office.

 

General Requirements

·  Phase I:  Your presentation should include Literature Critique - review of the state-of-the-art of the topic. In particular, in depth analysis of at least 2 papers on the topic.

·  Phase II: Implementation - select at least two techniques for comparison however you should implement only one of them.

·  Experiments - use available databases

Notes on Presentation for Phase I

·  I expect the presentation to last for 20 minutes (at most) and 10 minutes for questions and answers

·  The presentation should concentrate on the theoretical aspect of the techniques proposed by the authors. Examples of topics to be included:

    1. The rationale of the proposed biometrics (very brief)
    2. How the data is acquired.
    3. What features are to be extracted.
    4. How the features are to be extracted.
    5. How the features are trained.
    6. What is the classification scheme?

·  Your critical opinions on the proposed techniques, i.e., the advantages and disadvantages, should be presented.

·  If some of your papers are from the same authors, try to differentiate the difference (improvement) between the papers. When these papers are published in different journals/conferences at different times, there must be some improvements made in the "same" technique.

·  You will be evaluated on

    1. The "look" of your presentation (this is quite subjective)
    2. The clarity of the presentation
    3. The "style" of your presentation (subjective too)
    4. The content of the presentation
    5. The timing of the presentation

    Presentation schedule will be shortly announced in the class.

Notes on Presentation for Phase II

·  The presentation should last 20 minutes and the demo. 10 minutes. We can have 5 minutes of questions and answer.

·  Topics to be covered include (but not limited to) the following:

    1. How do you acquire (or obtain) the data?
    2. How do you extract the features?
      Present the algorithm step-by-step.
    3. How do you do verification with an input data?
    4. The performance of your experiment, i.e. the FAR and FRR or confusion matrix.

·  You will be evaluated on

    1. The "look" of your presentation
    2. The clarity of your presentation
    3. The "style" of your presentation
    4. The content of your presentation
    5. The timing of your presentation
    6. How clearly you present your demo.
    7. Whether your demo works or not.

·  Based on your project topics, I think all your input data will be images. Therefore, please inform me of the image format that your system will use. I'll "bring" some test data to evaluate the performance.

    Presentation schedule will be shortly announced in the class.

Notes on Project Report

 

  • Your project report should include the following sections:

  1. Introduction - rationale on why you choose the particular biometrics. Just elaborate on the introduction of your first presentation.
  2. Review of the state-of-the-arts - this covers the first presentation, i.e. the four papers. Please do not "copy" paragraphs from the original papers. Rewrite the descriptions in your own words. Of course, you have to put down the original equations from the papers.
  3. Implementation and Experimental Results - this covers the demo presentation. Performance analysis and your codes are to be included.
  4. Conclusion and Future Work - this section summarizes the project and lessons learned. Your view of possible future work should be included.
  5. References - this section includes the list of references you have referred to in the project.
  6. Demo - this section should give the URL where I can test your system with my test data. Similar to what you have done in the assignment, give me the URL to download your system.

Some References for Hand Geometry Verification

1.  R. Sanchez-Reillo, C. Sanchez-Avila, A. Gonzales-Marcos, “Biometric identification through hand geometry measurements,” IEEE Trans. Patt. Anal. Machine Intell., vol. 22, pp. 1168-1171, Oct. 2000.

2.  C. Oden, A. Ercil, and B. Buke, “Combining implicit polynomials and geometric features for hand recognition,” Pattern Recognition Letters, vol. 24, pp. 2145-2152, 2003.

3. A. K. Jain, A. Ross, and S. Pankanti, “A Prototype hand geometry-based verification system,  Proc. AVBPA, pp. 166-171, Washington, DC, USA, 1999.

4. S. Malassiotis, N. Aifanti, and M. G. Strintzis, "Personal Authentication using 3-D Finger Geometry," IEEE Trans Information Forensics and Security, pp. 1-10, March 2006.

 

Some References for Face Recognition

  1. "Facial Feature Extraction and Pose Determination" by Athanasioa Nikolaidis, Ioannis Pitas
  2. "Face Recognition Using Eigenfaces" by Mathew A. Turk, Alex P. Pentland
  3. "Face Recognition using Holistic Fourier Invariant Features" by Jian Huang Lai, Pong C. Yuen, Guo Can Feng
  4. "On Internal Representations in Face Recognition Systems" by Maxim A. Grudin
  5. "Snake: Active Contour Models" by Michael Kass, Andrew Witkin and Demetri Terzopoulos

Some References for Fingerprint Identification

  1. Kovacs-Vajna, Z.M., "A fingerprint verification system based on triangular matching and dynamic time warping", IEEE Trans. Patt. Anal. Machine Intell., vol. 22, no. 11, pp. 1266 -1276, Nov.2000.
  2. A.K. Jain, L. Hong and R. Bolle, "On-line Fingerprint Verification", IEEE Trans. Patt. Anal. Machine Intell., vol. 19, no. 4, pp. 302-314, 1997.
  3. Wahab, A.; Chin, S.H.; Tan, E.C., “Novel approach to automated fingerprint recognition”, IEE Proceedings Vision, Image and Signal Processing, vol. 145, Issue: 3 , June 1998, Page(s): 160 –166
  4. Ratha, N.K.; Bolle, R.M.; Pandit, V.D.; Vaish, V., “Robust fingerprint authentication using local structural similarity”, Applications of Computer Vision, 2000, Fifth IEEE Workshop on. , 2000 Page(s): 29 –34
  5. L. Lam, S. Lee, and C.Y.Suen, “Thinning Methodologies-A Comprehensive Survey” IEEE Trans. Patt. Anal. Machine Intell., vol. 14, no. 9, p869-885, 1992
  6. A. K. Hrechak and J. A. Mchugh, “Automated fingerprint recognition using structural matching”, Pattern Recognition, 1990, 23, (8), pp. 893-904

 

Some References for Palmprint Identification

 

    1.  D. Zhang, W.K. Kong, J. You, and M. Wong, “On-line palmprint identification,” IEEE Trans. Patt. Anal. Machine Intell., vol. 25, pp. 1041-1050, Sep. 2003.

    2. D. Zhang and W. Shu, “Two novel characteristics in palmprint verification: datum point invariance and line feature matching,” Pattern Recognition, vol. 32, no. 4, pp. 691-702, Apr. 1999.

    3. X. Lu, D. Zhang, K. Wang, “Fisherpalms based palmprint recognition,” Pattern Recognition Lett., vol. 24, pp. 2829-2838, Nov. 2003.

    4. "Matching of Palmprint", N. Duta, A. K. Jain, and Kanti V. Mardia, Pattern Recognition Lett., 2001.

   5. "Feature extraction method for palmprint considering elimination of creases ", Funada, J.; Ohta, N.; Mizoguchi, M.; Temma, T.; Nakanishi, K.; Murai, A.; Sugiuchi, T.;  Wakabayashi, Fourteenth International Conference on Pattern Recognition, Vol. 2, pp. 1849 -1854, 1998