Sage Journals: Discover world-class research

Abstract

There are lots of line traces on the surface of the broken ends which left in the cable cutting case crime scene along the high-speed railway in China. The line traces usually present nonlinear morphological features and has strong randomness. It is not very effective when using existing image-processing and three-dimensional scanning methods to do the trace comparison, therefore, a fast algorithm based on wavelet domain feature aiming at the nonlinear line traces is put forward to make fast trace analysis and infer the criminal tools. The proposed algorithm first applies wavelet decomposition to the 1-D signals which picked up by single point laser displacement sensor to partially reduce noises. After that, the dynamic time warping is employed to do trace feature similarity matching. Finally, using linear regression machine learning algorithm based on gradient descent method to do constant iteration. The experiment results of cutting line traces sample data comparison demonstrate the accuracy and reliability of the proposed algorithm.

Keywords

Signal detection wavelet transforms lasers machine learning

Get full access to this article

View all access options for this article.

References

Bunch and

Wevers , Application of likelihood ratios for firearm and toolmark analysis, Science and Justice 53(2) (2013), 223–229.

Liu ,

Pan ,

Sha , et al., One police laser detection system for linear traces, China Patent, CN 105300996 A, 2016, 02, 03. (in Chinese)

Gambino ,

Mclaughlin ,

Kuo , et al., Forensic surface metrology: Tool mark evidence, Scanning 33(5) (2011), 272–278.

Baiker ,

Keereweer ,

Pieterman , et.al., Quantitative comparison of striated toolmarks, Forensic Science International 242 (2014), 186–199.

Kassamakov ,

Barbeau ,

Lehto , et al., CSI Helsinki: Comparing three-dimensional imaging of diagonal cutter toolmarks using confocal microscopy and SWLI, Three-Dimensional Imaging, Visualization, and Display 2010 and Display Technologies and Applications for Defense, Security, and Avionics IV, Orlando, FL, United States, 2010, 7690:76900Y.

Yang ,

D.Y.

Li and

W.D.

Wang , The study of tool mark identification based on local wavelet energy, Journal of People's Public Security University of China(Science and Technology) 56 (2008), 73–75.

B.C.

Wang ,

Z.H.

Ren ,

L.Y.

Ren , et al., Fractal geometry description of the surface appearance of the shearing trace, Machinery Design & Manufacture 160 (2003), 106–107.

Pan ,

Wu ,

Liu , et al., Research on the adaptive matching algorithm for laser linear mark detection signals, Chinese Journal of Scientific Instrument 36(6) (2015), 1372–1380.

H.L.

Cui ,

Liu ,

Yu , et al., Application of wavelet denoising in distributed optical fiber interferometric vibration detection and location system, Optics and Precision Engineering 23 (2015), 71–76.

10.

S.L.

Ye ,

Y.D.

Zhang and

Zhang , Scale and directional correlation combined denoiseing in gear visual inspection, Optics and Precision Engineering 22(6) (2014), 1622–1630.

11.

M.Z.

Zhang ,

J.H.

Mou ,

Liu , et al., Phase extraction for fringe patterns based on complex Morlet wavelet transform, Optics and Precision Engineering 20(3) (2012), 643–650.

12.

Ogawa ,

Sakata and

Li , Adaptive noise reduction of scintigrams with a wavelet transform, Hindawi Publishing Corporation 2012(11) (2011), 130482.

13.

Zheng ,

L.M.

Xiao ,

W.Q.

Tang , et al., Parallelization of dynamic time warping on a heterogeneous platform, Maruzen Co, Ltd E97A(11) (2014), 2258–2262.

14.

H.L.

Li , On-line and dynamic time warping for time series data mining, Springer Verlag 6 (2014), 145–153.

15.

Dupas ,

Tavenard and

Ophelie , Identifying seasonal patterns of phosphorus storm dynamics with dynamic time warping, Blackwell Publishing Ltd 51 (2015), 8868–8882.

16.

Jia and

E.Y.

Lam , Machine learning for inverse lithography: Using stochastic gradient descent for robust photomask synthesis, Institute of Physics Publishing 12(4) (2010), 45601–45609.

17.

Shao and

J.Y.

Yang , Multi-robot reinforcement learning based on learning classifier system with gradient descent methods, Binary Information Press 6 (2010), 2449–2455.

Nonlinear tool traces fast tracing algorithm based on single point laser detection

Abstract

Keywords

Get full access to this article

References