Handwriting represents an important modality in both biometric and forensic domains. while the first field appears to be a well-studied area with many approaches for acquisition, feature extraction and classification, the latter is rather novel with respect to digitised, automated methods. In prior works, authors of this article have shown that forensic handwriting traces can be processed by means of high-resolution 2D/3D surficial scanners. These devices allow the acquisition at a vertical resolution down to a few nanometres. Pre-processing methods have been identified, which allow for spatial segmentation of writing traces and for de-noising of 2D and 3D data, leading to a clear visual enhancement of the writing traces based on topography information. Further, authors have suggested a novel benchmarking method for forensic trace analysis based on feature sets originally suggested for biometric handwriting and comparing the forensic recognition performance by means of equal error rates, achieved from biometric sensors and forensic 2D/3D sensors in parallel. This article summarises and extents these works in two main aspects: on one side, it presents significantly extended experiments with respect to test set size and feature sets utilised for classification. On the other side, authors suggest new optimisation approaches to the segmentation algorithm.

References

1. 1)
  - 30. StepOver: ‘naturaSign Pad Classic’, 2016. https://www.stepover.com/en-gb/signature-pads/naturasign-pad-classic/, assessed 14 July 2016.
2. 2)
  - 31. Seiko Epson Corporation: ‘Epson expression premium XP-830 small-in-one allin-one printer’, 2016. http://www.epson.co.uk/products/printers/inkjet-printers/consumer/expression-premium-xp-830, accessed 20 July 2016.
3. 3)
  - 32. Anand, M., Narasimha, Y.: ‘Removal of salt and pepper noise from highly corrupted images using mean deviation statistical parameter’, Int. J. Comput. Sci. Eng., 2013, 5, (2), pp. 113–119.
4. 4)
  - 16. Geradts, Z.: ‘Content based information retrieval from forensic image databases’. Ph.D. thesis, University of Utrecht, 2002.
5. 5)
  - 1. Ellen, D.: ‘Scientific examination of documents: methods and techniques, third edition, international forensic science and investigation’ (CRC Press, 2005, 3rd edn.).
6. 6)
  - 3. Kalbitz, M., Scheidat, T., Vielhauer, C.: ‘First investigation of feasibility of contact-less non-destructive optical sensors to detect, acquire and digitally process forensic handwriting based on pressure information’. 2016 4th Int. Conf. on Biometrics and Forensics (IWBF), March 2016, pp. 1–6.
7. 7)
  - 8. Mohammed, R.A., Nabi, R.M., Mahmood, S.M.R., et al: ‘State-of-the-art in handwritten signature verification system’. 2015 Int. Conf. on Computational Science and Computational Intelligence (CSCI), December 2015, pp. 519–525.
8. 8)
  - 22. Arndt, C., Kraetzer, C., Vielhauer, C.: ‘First approach for a computer-aided textile fiber type determination based on template matching using a 3d laser scanning microscope’. MM&Sec 2012 Proc. Multimedia and Security Workshop, 2012, pp. 57–66.
9. 9)
  - 6. Al-Omari, Y.M., Abdullah, S.N.H.S., Omar, K.: ‘State-of-the-art in offline signature verification system’. 2011 Int. Conf. on Pattern Analysis and Intelligence Robotics, 2011, vol. 1, pp. 59–64.
10. 10)
  - 18. Foster + Freeman: ‘ESDA 2’, 2016. http://www.fosterfreeman.com/index.php/fingerprint-evidence/esda-2-col-180-electrostatic-imaging-device, assessed on 11 July 2016.
11. 11)
  - 21. Hildebrandt, M., Dittmann, J.: ‘Benchmarking contactless acquisition sensor reproducibility for latent fingerprint trace evidence’, 2015.
12. 12)
  - 23. Fischer, R., Vielhauer, C.: ‘Towards automated firearm identification based on high resolution 3D data: rotation-invariant features for multiple line-profile-measurement of firing pin shapes’. Proc. SPIE Three-Dimensional Image Processing, Measurement (3DIPM), and Applications, 2015.
13. 13)
  - 2. Vielhauer, C.: ‘Biometric user authentication for IT security: from fundamentals to handwriting’ (Springer, New York, 2006).
14. 14)
  - 27. Zhang, Y.J.: ‘A survey on evaluation methods for image segmentation’, Pattern Recognit., 1996, 29, (8), pp. 1335–1346.
15. 15)
  - 20. Hildebrandt, M., Merkel, R., Leich, M., et al: ‘Benchmarking contact-less surface measurement devices for fingerprint acquisition in forensic investigations: results for a differential scan approach with a chromatic white light sensor’. Proc. 17th Int. Conf. on Digital Signal Processing (DSP), 2011.
16. 16)
  - 13. Wayman, J., Orlans, N., Hu, Q., et al: ‘Technology assessment for the state of the art biometrics excellence roadmap’. Technical Report 2, The MITRE Corporation, 2009.
17. 17)
  - 26. Sahoo, P.K., Soltani, S.A.K.C., Wong, A.K.C.: ‘A survey of thresholding techniques’, Comput. Vis. Graph. Image Process., 1988, 41, (2), pp. 233–260.
18. 18)
  - 4. Scheidat, T., Kalbitz, M., Vielhauer, C.: ‘Towards biometric features for 2D/3D sensoring of forensic handwriting’. 2016 First Int. Workshop on Sensing, Processing and Learning for Intelligent Machines (SPLINE), July 2016.
19. 19)
  - 10. Bundeskriminalamt: ‘Handwritten extortion letters’, 2017. https://www.bka.de/EN/OurTasks/SupportOfInvestigationAndPrevention/ForensicScience/PhysicalEvidence/Extortion/HandwrittenExtortionLetters/handwrittenextortionletters_node.html, accessed 09 January2017.
20. 20)
  - 35. Vielhauer, C., Steinmetz, R., Mayerhoefer, A.: ‘Biometric hash based on statistical features of online signatures’. Int. Conf. on Pattern Recognition, 2002, 1, p. 10123.
21. 21)
  - 19. Radley, R.W.: ‘Forensic examination services – ESDA’, 2016. http://www.docexam.co.uk/esda.html, assessed on 11 July 2016.
22. 22)
  - 25. Freixenet, J., Muñoz, X., Raba, D., et al: ‘Yet another survey on image segmentation: region and boundary information integration’. European Conf. on Computer Vision, 2002, pp. 408–422.
23. 23)
  - 34. Makrushin, A., Scheidat, T., Vielhauer, C.: ‘Improving reliability of biometric hash generation through the selection of dynamic handwriting features’, in Shi, Y.Q., Katzenbeisser, S. (Eds.): Transactions on Data Hiding and Multimedia Security VIII – Special Issue on Pattern Recognition for IT Security, 2012, 7228, pp. 19–41.
24. 24)
  - 28. Nobuyuki Otsu: ‘A threshold selection method from gray-level histogram’, IEEE Trans. Syst. Man Cybern., 1979, 9, (1), pp. 62–66.
25. 25)
  - 24. Zhang, H., Fritts, J.E., Goldman, S.A.: ‘Image segmentation evaluation: a survey of unsupervised methods’, Comput. Vis. Image Underst., 2008, 110, (2), pp. 260–280.
26. 26)
  - 7. Khan, S., Dhole, A.: ‘A review on offline signature recognition and verification techniques’, Int. J. Adv. Res. Comput. Commun. Eng., 2014, 3, (6), pp. 79–82.
27. 27)
  - 15. Gannon Technologies Group: ‘Search the unsearchable’, 2017. http://gannontech.com/, assessed 14 February 2017.
28. 28)
  - 14. Cedartech: ‘Cedartech ::: pattern recognition technology’, 2017. http://www.cedartech.com/products_cedarfox.html, assessed 14 February 2017.
29. 29)
  - 11. Franke, K., Köppen, M.: ‘A computer-based system to support forensic studies on handwritten documents’, Int. J. Doc. Anal. Recogn., 2001, 3, (4), pp. 218–231.
30. 30)
  - 17. Kroon, L.: ‘Computer aided analysis of handwriting by the NIFO-TNO approach’. Proc. of the 4th European Handwriting Conf. for Police and Government Handwriting Experts, London, October 1994, pp. 40–53.
31. 31)
  - 29. ‘Chromatic White Light Sensor FRT CWL – Fries Research & Technology GmbH’, 2016. http://www.frt-gmbh.com/en/chromatic-white-light-sensor-frt-cwl.aspx, assessed 27 June 2016.
32. 32)
  - 5. Kalbitz, M., Scheidat, T., Vielhauer, C.: ‘Investigation of adaptive local threshold segmentation in context of 3D-handwriting forensics’. 2016 Sixth Int. Conf. on Image Processing Theory, Tools and Applications (IPTA), December 2016, pp. 1–6.
33. 33)
  - 33. The MathWorks, Inc: ‘imregister – intensity-based image registration’, 2016. http://mathworks.com/help/images/ref/imregister.html, assessed 21 April 2016.
34. 34)
  - 12. Köller, N. (Ed): ‘Probability conclusions in expert opinions on handwriting – substantiation and standardization of probability statements in expert opinions, Polizei+Forschung 26’ (Luchterhand, München, 2004).
35. 35)
  - 9. Bundeskriminalamt: ‘The computer as detective: (special information systems)’, 2017. https://www.bka.de/EN/OurTasks/SupportOfInvestigationAndPrevention/Technologies/SpecialInformationSystems/specialinformationsystems_node.html, accessed 09 January 2017.

Biometric authentication based on 2D/3D sensing of forensic handwriting traces

References

Related content