Spectral Fiber Feature Space Evaluation for Crime Scene Forensics - Traditional Feature Classification vs. BioHash Optimization

Christian Arndt, Jana Dittmann, Claus Vielhauer

Abstract

Despite of ongoing improvements in the field of digitized crime scene forensics, a lot of analysis work is still done manually by trained experts. In this paper, we derive and define a 2048 dimensional fiber feature space from a spectral scan with a wavelength range of 163 - 844 nm sampled with FRT thin film reflectometer (FTR). Furthermore, we perform an evaluation of seven commonly used classifiers (Naive Bayes, SMO, IBk, Bagging, Rotation Forest, JRip, J48) in combination with a proven concept from the biometric field of user authentication called Biometric Hash algorithm (BioHash). We perform our evaluation in two well-known forensic examination goals: identification - determining the broad fiber group (e.g. acrylic) and individualization - finding the concrete textile originator. Our experimental test set considers 50 different fibers, each sampled in four scan resolutions of: 100; 50; 20; 10 μm. Overall, 800 digital samples are measured. For both examination goals we can show that despite the Naive Bayes all classifiers show a positive classification tendency (80 - 99%), whereby the BioHash optimization performs best for individualization tasks.

References

  1. (2000). Standard test methods for identification of fibers in textiles.
  2. Appalaneni, K., Heider, E. C., Moore, A. F. T., and Campiglia, A. D. (2014). Single fiber identification with nondestructive excitation-emission spectral cluster analysis. Analytical Chemistry, 86(14):6774- 6780. PMID: 24432828.
  3. Arndt, C., Kraetzer, C., and Vielhauer, C. (2012). First approach for a computer-aided textile fiber type determination based on template matching using a 3d laser scanning microscope. In Proceedings of the 14th workshop on Multimedia and Security, MMSec 7812, pages 57-66. ACM, New York, NY, USA.
  4. Fries Research & Technology GmbH (FRT) (2010). Data sheet frt ftr - thin film reflectometer.
  5. Hall, M., Frank, E., Holmes, G., Pfahringer, B., Reutemann, P., and Witten, I. H. (2009). The WEKA data mining software: an update. SIGKDD Explor. Newsl., 11(1):10-18.
  6. Hildebrandt, M., Arndt, C., Makrushin, A., and Dittmann, J. (2012). Computer-aided fiber analysis for crime scene forensics. In Bouman, C. A., Pollak, I., and Wolfe, P. J., editors, Proc. of SPIE 8296, Computational Imaging X, 829601, volume 8296.
  7. Hildebrandt, M., Makrushin, A., Qian, K., and Dittmann, J. (2013). Visibility assessment of latent fingerprints on challenging substrates in spectroscopic scans. In De Decker, B., Dittmann, J., Kraetzer, C., and Vielhauer, C., editors, Communications and Multimedia Security, volume 8099 of Lecture Notes in Computer Science, pages 200-203. Springer Berlin Heidelberg.
  8. Houck, M. M. and Siegel, J. A. (2010). Fundamentals of Forensic Science. Academic Press, 2nd edition edition.
  9. Inman, K. and Rudin, N. (2001). Principles and Practice of Criminalistics - The Profession of Forensic Science. CRC Press.
  10. Jain, A. K. (1989). Fundamentals of Digital Image Processing. Prentice Hall.
  11. Kurabayashi, T., Saitoh, F., Watanabe, N., and Tanno, T. (2010). Identification of textile fiber by terahertz spectroscopy. In Proc: 35th International Conference on Infrared Millimeter and Terahertz Waves (IRMMWTHz), pages 1-2.
  12. Millington, K. R. (2012). Diffuse reflectance spectroscopy of fibrous proteins. Amino Acids, 43(3):1277-1285.
  13. Platt, J. C. (1998). Sequential minimal optimization: A fast algorithm for training support vector machines. Technical report, Advances in Kernel Methods - Support Vector Learning.
  14. Prange, A., Reus, U., Boeddeker, H., Fischer, R., and Adolf, F.-P. (1995). Microanalysis in forensic science: Characterization of single textile fibers by total reflection x-ray fluorescence. In Analytical Sciences, volume 11, pages 483-487.
  15. Stoeffler, S. (1996). A flowchart system for the identification of common synthetic fibers by polarized light microscopy. Journal of Forensic Sciences, 41:297-299.
  16. SWGMAT (1999). Forensic fiber examination guidelines. Online available: http://www.swgmat.org/Forensic %20Fiber%20Examination%20Guidelines.pdf.
  17. Vielhauer, C. (2006). Biometric User Authentication for IT Security - from Fundamentals to Handwriting. Springer Science+Business Media, Inc.
  18. Vielhauer, C., Steinmetz, R., and Mayerhofer, A. (2002). Biometric hash based on statistical features of online signatures. In Pattern Recognition, 2002. Proceedings. 16th International Conference on, volume 1, pages 123-126.
  19. Witten, I. H., Frank, E., and Hall, M. A. (2011). Data Mining Practical Machine Learning Tools and Techniques. Elsevier, 3. auflage edition.
Download


Paper Citation


in Harvard Style

Arndt C., Dittmann J. and Vielhauer C. (2015). Spectral Fiber Feature Space Evaluation for Crime Scene Forensics - Traditional Feature Classification vs. BioHash Optimization . In Proceedings of the 10th International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2015) ISBN 978-989-758-089-5, pages 293-302. DOI: 10.5220/0005270402930302


in Bibtex Style

@conference{visapp15,
author={Christian Arndt and Jana Dittmann and Claus Vielhauer},
title={Spectral Fiber Feature Space Evaluation for Crime Scene Forensics - Traditional Feature Classification vs. BioHash Optimization},
booktitle={Proceedings of the 10th International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2015)},
year={2015},
pages={293-302},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0005270402930302},
isbn={978-989-758-089-5},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 10th International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2015)
TI - Spectral Fiber Feature Space Evaluation for Crime Scene Forensics - Traditional Feature Classification vs. BioHash Optimization
SN - 978-989-758-089-5
AU - Arndt C.
AU - Dittmann J.
AU - Vielhauer C.
PY - 2015
SP - 293
EP - 302
DO - 10.5220/0005270402930302