Advertisement

Detection of the Toe-off Feature of Planar Shoeprint Based on CNN

  • Xiangyu Meng
  • Yunqi Tang
  • Wei Guo
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10996)

Abstract

In Chinese forensic science, a planar footprint can provide police office lots of information, such as sex, age and gait for criminal investigation. The toe-off feature is an important feature of planar shoeprint, which can indicate the gait pattern of the walkers. However, the toe-off features of planar shoeprints are still analyzed artificially by criminal investigators, which is inefficient and subjective. In this research, a novel algorithm for the automatic detection of the toe-off feature is developed. We define the crescent feature in the toe-off feature of planar footprint as a positive sample, and define no such feature as a negative sample. We use CNN to detect them. In order to conduct the research, we take photo of planar shoeprints by the way of criminal scene photography. After performing some pre-processing steps on these pictures, we set up a planar shoeprint database. Experimental results show that the proposed method achieves detection accuracy of 97.0% on our planar shoeprint database.

Keywords

Toe-off feature Planar shoeprint Convolutional Neural Network Detection 

Notes

Acknowledgments

This work is supported by the National Key Research and Development Program (Grant No. 2017YFC0803506), the Fundamental Research Funds for the Central Universities of China (Grant No. 2018JKF217), the National Natural Science Foundation of China (Grant No. 61503387).

References

  1. 1.
    Castro, F.M., Mata, N.G.: Fisher motion descriptor for multiview gait recognition. Int. J. Pattern Recognit Artif Intell. 31(01), 1756002 (2016)CrossRefGoogle Scholar
  2. 2.
    Mansur, A., Makihara, Y., Aqmar, R., et al.: Gait recognition under speed transition. In: Computer Vision and Pattern Recognition, pp. 249–257. IEEE (2014)Google Scholar
  3. 3.
    Chen, X., Huang, K., Tan, T.: Object Tracking Across Non-overlapping Views by Learning Inter-camera Transfer Models. Elsevier Science Inc., New York (2014)Google Scholar
  4. 4.
    Ma, Y.: Gait recognition using sparse representation. In: IEEE International Conference on Wavelet Analysis and Pattern Recognition, pp. 136–139 (2010)Google Scholar
  5. 5.
    Liu, Z., Malave, L., Sarkar, S.: Studies on silhouette quality and gait recognition. In: Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 704–711 (2004)Google Scholar
  6. 6.
    Shi, L., et al.: Footprint 足迹学. People’s Public Security University of China, Beijing (2007)Google Scholar
  7. 7.
    Sugimoto, C., Tsuji, M., Lopez, G., et al.: Development of a behavior recognition system using wireless wearable information devices. In: International Symposium on Wireless Pervasive Computing, p. 5. IEEE (2006)Google Scholar
  8. 8.
    Takeda, T., Kuramoto, K., Kobashi, S., et al.: Biometrics personal identification by wearable pressure sensor. In: Fifth International Conference on Emerging Trends in Engineering and Technology, pp. 120–123. IEEE Computer Society (2012)Google Scholar
  9. 9.
    Han, D., Yunqi, T., Wei, G.: Research on the stability of plantar pressure under normal walking condition. In: Tan, T., Li, X., Chen, X., Zhou, J., Yang, J., Cheng, H. (eds.) CCPR 2016. CCIS, vol. 662, pp. 234–242. Springer, Singapore (2016).  https://doi.org/10.1007/978-981-10-3002-4_20CrossRefGoogle Scholar
  10. 10.
    Jing, M.Q., Ho, W.J., Chen, L.H.: A novel method for shoeprints recognition and classification. In: International Conference on Machine Learning and Cybernetics, pp. 2846–2851. IEEE (2009)Google Scholar
  11. 11.
    Anusudha, K.: Threshold value determination for recognition of partial shoe prints for forensic analysis. Digit. Image Process. 5(1), 7–13 (2013)Google Scholar
  12. 12.
    Sun, H., Tang, Y., Guo, W.: Research on dig-imprint detection of three-dimensional footprints. In: Zhou, J., et al. (eds.) CCBR 2017. LNCS, vol. 10568, pp. 495–502. Springer, Cham (2017).  https://doi.org/10.1007/978-3-319-69923-3_53CrossRefGoogle Scholar
  13. 13.
    Sandoval, H., Hattori, T., Kitagawa, S., et al.: A filter of concentric shapes for image recognition and its implementation in a modified DT-CNN. IEICE Trans. Fund. Electron. Commun. Comput. Sci. 95(9), 2189–2197 (2001)Google Scholar
  14. 14.
    Saatci, E., Tavsanoglu, V.: Multiscale handwritten character recognition using CNN image filters, vol. 3, pp. 2044–2048 (2002)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2018

Authors and Affiliations

  1. 1.School of Forensic SciencePeople’s Public Security University of ChinaBeijingChina

Personalised recommendations