Recognition of Untrustworthy Face Images in ATM Sessions using a Bio-inspired Intelligent Network

R. Škoviera, K. Valentín, S. Štolc, I. Bajla

Abstract

The aim of this paper is to report on a pilot application of a bio-inspired intelligent network model, called Hierarchical Temporal Memory (HTM), for recognition (detection) of untrustworthy manipulation with an Automatic Teller Machine (ATM). HTM was used as a crucial part of an anomaly detection system to recognize hard-to-identifiable faces, i.e., faces with a mask, covered with a scarf, or wearing sunglasses. Those types of face occlusion can be a good indicator of potentialy malicious intentions of an ATM user. In the presented system, the Kinect camera was used for acquisition of video image sequences. The Kinect’s depth output along with skeleton tracking was used as a basis of the color image segmentation. To test the proposed system, experiments have been carried out in which several participants performed normal and untrustworthy actions using an ATM simulator. The output of the face classification system can assist a security personnel in surveillance tasks.

References

  1. Daugman, J. G. (1985). Uncertainty relation for resolution in space, spatial frequency, and orientation optimized by two-dimensional visual cortical filters. Journal of the Optical Society of America A Optics and image science, 2(7):1160-1169.
  2. Dong, W. T. and Soh, Y. S. (2006). Image-based fraud detection in automatic teller machine. IJCSNS, 6(11):13.
  3. George, D. (2008). How the brain might work: A hierarchical and temporal model for learning and recognition. PhD thesis, Stanford.
  4. George, D. and Hawkins, J. (2005). A hierarchical Bayesian model of invariant pattern recognition in the visual cortex. In Prokhorov, D., editor, Proceedings of the International Joint Conference on Neural Networks (IJCNN), volume 3, pages 1812-1817.
  5. George, D. and Hawkins, J. (2009). Towards a mathematical theory of cortical micro-circuits. PLoS Computational Biology, 5(10):e1000532.
  6. Hawkins, J. and Blakeslee, S. (2004). Henry Holt and Company, New York.
  7. Johnson, S. (1967). Hierarchical clustering schemes. Psychometrika, 32:241-254.
  8. Kostavelis, I. and Gasteratos, A. (2012). On the optimization of hierarchical temporal memory. Pattern Recognition Letters, 33(5):670-676.
  9. Lin, D. T. and Liu, M. J. (2006). Face Occlusion Detection for Automated Teller Machine Surveillance. In Chang, L.-W. and Lie, W.-N., editors, Advances in Image and Video Technology, volume 4319 of Lecture Notes in Computer Science, pages 641-651. Springer Berlin / Heidelberg.
  10. Numenta (2009). Numenta node algorithms guide, NuPIC 1.7.
  11. Rozado, D., Agustin, J. S., Rodriguez, F. B., and Varona, P. (2012). Gliding and saccadic gaze gesture recognition in real time. ACM Transactions on Intelligent Interactive Systems, 1(2):1-27.
  12. Suhr, J. K., Eum, S., Jung, H. G., Li, G., Kim, G., and Kim, J. (2012). Recognizability assessment of facial images for automated teller machine applications. Pattern Recognition, 45(5):1899-1914.
  13. Thornton, J., Faichney, J., Blumenstein, M., and Hine, T. (2008). Character recognition using hierarchical vector quantization and temporal pooling. In Proceedings of the 21st Australasian Joint Conference on Artificial Intelligence: Advances in Artificial Intelligence, AI 7808, pages 562-572, Berlin, Heidelberg. SpringerVerlag.
  14. Štolc, S. and Bajla, I. (2009). Image object recognition based on biologically inspired Hierarchical Temporal Memory model and its application to the USPS database. In Tyšler, M., editor, 7th International Conference MEASUREMENT 2009, pages 23-27, Smolenice, Slovak Republic.
  15. Štolc, S. and Bajla, I. (2010a). Application of the computational intelligence network based on hierarchical temporal memory to face recognition. In Hamza, M. H., editor, 10th IASTED International Conference on Artificial Intelligence and Applications AIA 2010, pages 185-192, Innsbruck, Austria. ACTA Press.
  16. Štolc, S. and Bajla, I. (2010b). On the Optimum Architecture of the Biologically Inspired Hierarchical Temporal Memory Model Applied to the Hand-Written Digit Recognition. Measurement Science Review, 10(2):28- 49.
  17. Wen, C., Chiu, S., Tseng, Y., and Lu, C. (2005). The mask detection technology for occluded face analysis in the surveillance system. Journal of Forensic Sciences, 50(3):1-9.
Download


Paper Citation


in Harvard Style

Škoviera R., Valentín K., Štolc S. and Bajla I. (2013). Recognition of Untrustworthy Face Images in ATM Sessions using a Bio-inspired Intelligent Network . In Proceedings of the 2nd International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM, ISBN 978-989-8565-41-9, pages 511-517. DOI: 10.5220/0004195605110517


in Bibtex Style

@conference{icpram13,
author={R. Škoviera and K. Valentín and S. Štolc and I. Bajla},
title={Recognition of Untrustworthy Face Images in ATM Sessions using a Bio-inspired Intelligent Network},
booktitle={Proceedings of the 2nd International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,},
year={2013},
pages={511-517},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0004195605110517},
isbn={978-989-8565-41-9},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 2nd International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,
TI - Recognition of Untrustworthy Face Images in ATM Sessions using a Bio-inspired Intelligent Network
SN - 978-989-8565-41-9
AU - Škoviera R.
AU - Valentín K.
AU - Štolc S.
AU - Bajla I.
PY - 2013
SP - 511
EP - 517
DO - 10.5220/0004195605110517