Skip to main content
SpringerLink
Log in

Real-time and robust multiple-view gender classification using gait features in video surveillance

  • Theoretical advances
  • Published:
Pattern Analysis and Applications Aims and scope Submit manuscript

Abstract

It is common to view people in real applications walking in arbitrary directions, holding items, or wearing heavy coats. These factors are challenges in gait-based application methods, because they significantly change a person‘s appearance. This paper proposes a novel method for classifying human gender in real time using gait information. The use of an average gait image, rather than a gait energy image, allows this method to be computationally efficient and robust against view changes. A viewpoint model is created for automatically determining the viewing angle during the testing phase. A distance signal model is constructed to remove any areas with an attachment (carried items, worn coats) from a silhouette to reduce the interference in the resulting classification. Finally, the human gender is classified using multiple-view-dependent classifiers trained using a support vector machine. Experiment results confirm that the proposed method achieves a high accuracy of 98.8% on the CASIA Dataset B and outperforms the recent state-of-the-art methods.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8

Similar content being viewed by others

References

  1. Romero-Garces A, Calderita LV, Martinez-Gomez J et al (2015) Testing a fully autonomous robotic salesman in real scenarios. In: IEEE international conference on autonomous robots systems and competitions, Vilareal, Portugal, p 17

  2. Burkhardt F, Eckert M, Johannsen W et al (2010) A database of age and gender annotated telephone speech. In: LREC, pp 1562–1565

  3. Meinedo H, Trancoso I (2010) Age and gender classification using fusion of acoustic and prosodic features. In: INTERSPEECH, p 2818–2821

  4. Chaudhari S, Kagalkar R (2012) A review of automatic speaker age classification, recognition and identifying speaker emotion using voice signal. Int J Sci Res 3(11):1307–1311

    Google Scholar 

  5. Golomb BA, Lawrence DT, Sejnowski TJ (1990) SEXNET: a neural network identifies sex from human faces. In: NIPS

  6. Graf AB, Wichmann FA (2002) Gender classification of human faces. In: Biologically motivated computer vision, Springer, pp 491–500

  7. Ziyi X, Li L, Pengfei S (2008) A hybrid approach to gender classification from face images. In: 19th International conference on pattern recognition, pp 1–4

  8. Hadid A, Pietikinen M (2009) Combining appearance and motion for face and gender recognition from videos. Pattern Recognit 42(11):2818–2827

    Article  Google Scholar 

  9. Khan MNA, Qureshi SA, Riaz N (2013) Gender classification with decision trees. Int J Signal Process Image Process Pattern Recognit 6(1):165–176

    Google Scholar 

  10. Levi G, Hassner T (2015) Age and gender classification using convolutional neural networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition workshops, pp 541–547

  11. Mkinen E, Raisamo R (2008) Evaluation of gender classification methods with automatically detected and aligned faces. IEEE Trans Pattern Anal Mach Intell 30(3):541–547

    Article  Google Scholar 

  12. Samek W, Binder A, Lapuschkin S et al (2017) Understanding and comparing deep neural networks for age and gender classification. In: International conference on computer vision workshop, pp 1629–1638

  13. Murray MP, Drought AB, Kory RC (1964) Walking patterns of normal men. J Bone Joint Surg Am 46(2):335–360

    Article  Google Scholar 

  14. Murray MP (1967) Gait as a total pattern of movement: including a bibliography on gait. Am J Phys Med Rehabil 46(1):290–333

    Google Scholar 

  15. Yu S, Tan D, Tan T (2006) Modelling the effect of view angle variation on appearance-based gait recognition. In: Asian conference on computer vision, Springer, pp 807–816

  16. Yu S, Tan D, Tan T (2006) A framework for evaluating the effect of view angle, clothing and carrying condition on gait recognition. In: 18th International conference on pattern recognition, pp 441–444

  17. Vapnik VN (1998) Statistical learning theory. Wiley, New York

    MATH  Google Scholar 

  18. Kozlowski LT, Cutting JE (1977) Recognizing the sex of a walker from a dynamic point-light display. Percept Psychophys 21(6):575–580

    Article  Google Scholar 

  19. Barclay CD, Cutting JE, Kozlowski LT (1978) Temporal and spatial factors in gait perception that influence gender recognition. Percept Psychophys 23(2):145–152

    Article  Google Scholar 

  20. Lee L, Grimson WEL (2002) Gait appearance for recognition. In: Biometric Authentication, Springer, pp 143–154

  21. Chew-Yean Y, N MS (2009) Model-based gait recognition. In: Encyclopedia of biometrics, pp 1082–1088

  22. Sudha L, Bhavani R (2012) Gait based gender identification using statistical pattern classifiers. Int J Comput Appl 40(8):30–35

    Google Scholar 

  23. Han J, Bhanu B (2006) Individual recognition using gait energy image. IEEE Trans Pattern Anal Mach Intell 28(2):316–322

    Article  Google Scholar 

  24. Hu M, Wang Y (2009) A new approach for gender classification based on gait analysis. In: Image and graphics, pp 869–874

  25. Yu S, Tan T, Huang K et al (2009) A study on gait-based gender classification. IEEE Trans Image Process 18(8):1905–1910

    Article  MathSciNet  Google Scholar 

  26. Zheng S, Zhang J, Huang K et al (2011) Robust view transformation model for gait recognition. In: 18th IEEE international conference on image processing, pp 2037–2076

  27. Lu J, Wang G, Huang TS (2012) Gait-based gender classification in unconstrained environments. In: 21st International conference on pattern recognition, pp 3284–3287

  28. Chen Y, Yang Y, Lee J (2015) Gait based gender classification using Kinect sensor. In: 122nd ASEE annual conference and exposition

  29. Chen L, Wang Y, Wang Y (2009) Gender classification based on fusion of weighted multi-view gait component distance. In: IEEE Chinese conference on pattern recognition, pp 1–5

  30. Makihara Y, Mannami H, Yagi Y (2010) Gait analysis of gender and age using a large-scale multi-view gait database. In: Asian conference on computer vision, Springer, pp 440–451

  31. Zhang D, Wang Y (2014) Using multiple views for gait-based gender classification. In: IEEE 26th Chinese control and decision conference, pp 2194–2197

  32. Choudhury SD, Tjahjadi T (2015) Robust view-invariant multiscale gait recognition. Pattern Recognit 48(3):798–811

    Article  Google Scholar 

  33. De Z (2015) Gender recognition based on gait using multi-view fusion. Open Cybern Syst J 9(2015):512–518

    Article  Google Scholar 

  34. De Z (2015) Research on gait-based gender classification via fusion of multiple views. Int J Database Theory Appl 8(5):39–50

    Article  Google Scholar 

  35. Kale A, Chowdhury AKR, Chellappa R (2003) Towards a view invariant gait recognition algorithm. In: Proceedings IEEE conference on advanced video and signal based surveillance, pp 143–150

  36. Hartley R, Zisserman A (2003) Multiple view geometry in computer vision. Cambridge University Press, Cambridge

    MATH  Google Scholar 

  37. Dalal N, Triggs B (2005) Histograms of oriented gradients for human detection. In: Computer vision and pattern recognition, pp 143–150

  38. Zivkovic Z (2004) Improved adaptive Gaussian mixture model for background subtraction. In: Proceedings of the 17th international conference on pattern recognition, pp 28–31

  39. Yoo J-H, Hwang D, Nixon MS (2005) Gender classification in human gait using support vector machine. In: International conference on advanced concepts for intelligent vision systems, Springer

  40. Birch I, Vernon W, Burrow G et al (2014) The effect of frame rate on the ability of experienced gait analysts to identify characteristics of gait from closed circuit television footage. Sci Justice 54(2):159–163

    Article  Google Scholar 

  41. Winter DA (2004) Biomechanics and motor control of human movement, 3rd edn. Wiley, New Jersey

    Google Scholar 

  42. Igual L, Lapedriza A, Borrs R (2013) Robust gait-based gender classification using depth cameras. EURASIP J Image Video Process 1(2013):1–11

    Article  Google Scholar 

  43. Wang Y-C, Kao C-W, Chen Y-N et al (2015) Local block-difference pattern for use in gait-based gender classification. J Inf Sci Eng 31(6):1993–2008

    Google Scholar 

  44. Lee L, Grimson WEL (2002) Gait analysis for recognition and classification. In: Proceedings of fifth IEEE international conference on automatic face and gesture recognition, pp 155–162

  45. Huang G, Wang Y (2007) Gender classification based on fusion of multi-view gait sequences. In: Asian conference on computer vision, Springer

  46. Li X, Maybank SJ, Yan S et al (2008) Gait components and their application to gender recognition. IEEE Trans Syst Man Cybern Part C Appl Rev 38(2):145–155

    Article  Google Scholar 

  47. Naini FB, Cobourne MT, McDonal F et al (2008) The influence of craniofacial to standing height proportion on perveived attractiveness. Int J Oral Maxillofac Surg 37(10):877–885

    Article  Google Scholar 

  48. Bogin B, Varela-Silva B, Ines M (2010) Leg length, body proportion, and health: a review with a note on beauty. Int J Environ Res Public Health 7(3):1047–1075

    Article  Google Scholar 

  49. Isaac ER, Elias S, Rajagopalan S et al (2018) Multiview gait-based gender classification through pose-based voting. Pattern Recognit Lett. https://doi.org/10.1016/j.patrec.2018.04.020

    Article  Google Scholar 

  50. Castro FM, Marn-Jimnez MJ, Guil N et al (2017) Automatic learning of gait signatures for people identification. In: International work-conference on artificial neural networks, Springer, pp 257–270

Download references

Author information

Authors and Affiliations

  1. Computer Vision Laboratory, Department of Information and Communication Engineering, Inha University, 525 Hightech Building, 100 Inha-ro, Michuhol-gu, Incheon, 22212, Korea

    Trung Dung Do & Hakil Kim

  2. Faculty of Information Technology, Ton Duc Thang University, Ho Chi Minh City, Vietnam

    Van Huan Nguyen

Authors
  1. Trung Dung Do
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Van Huan Nguyen
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Hakil Kim
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Van Huan Nguyen.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Do, T.D., Nguyen, V.H. & Kim, H. Real-time and robust multiple-view gender classification using gait features in video surveillance. Pattern Anal Applic 23, 399–413 (2020). https://doi.org/10.1007/s10044-019-00802-6

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10044-019-00802-6

Keywords

Search

Navigation