Page - 112 - in Proceedings of the OAGM&ARW Joint Workshop - Vision, Automation and Robotics

ACKNOWLEDGEMENTS This work has been funded by the Austrian security research programme KIRAS of the Federal Ministry for Transport, Innovation and Technology (bmvit) under Grant 850193. We would like to thank the forensic experts of the Criminal Intelligence Service Austria and the LKA Wien (AB08 KPU) for their help. The Titan X used for this research was donated by the NVIDIA Corporation. REFERENCES [1] M. Baiker, I. Keereweer, R. Pieterman, E. Vermeij, J. van der Weerd, and P. Zoon, “Quantitative comparison of striated toolmarks,”Forensic Science International, vol. 242, pp. 186–199, 2014. [2] V. Balntas, E. Johns, L. Tang, and K. Mikolajczyk, “PN-Net: Conjoined Triple Deep Network for Learning Local Image Descriptors,” ArXiv, 2016. [3] M. Keglevic and R. Sablatnig, “Learning a Similarity Measure for Stri- ated Toolmarks using Convolutional Neural Networks,” inProceedings of the7th IETInternationalConferenceonImaging forCrimeDetection and Prevention (ICDP), 2016. [4] O.M.Parkhi,A.Vedaldi, andA.Zisserman,“Deepface recognition,” in Proceedings of the BritishMachine Vision Conference (BMVC), 2015. [5] R. Spotts, L. S. Chumbley, L. Ekstrand, S. Zhang, and J. Kreiser, “Optimization of a Statistical Algorithm for Objective Comparison of Toolmarks,” Journal of Forensic Sciences, vol. 60, no. 2, pp. 303–314, 2015. 112