access icon free Gait features fusion for efficient automatic age classification

© The Institution of Engineering and Technology
Received 02/02/2017, Accepted 27/07/2017, Revised 22/06/2017, Published 01/08/2017

Far from the camera, image resolution is significantly degraded and person cannot cooperate with the acquisition equipment. So, the classical intrusive biometrics approach could not be applied. As a non-intrusive biometric, gait analysis gained the attention of the computer vision community for number of potential applications such as age estimation. Since, that gait is very sensitive to ageing, gait analysis is the suitable solution for age estimation at a great distance from the camera. Given the complexity of this task, the authors propose in this study a new approach based on descriptors cascade. The proposed approach is to use a fusion of some efficient contour and silhouette descriptors. Indeed, they introduce the proposed descriptor based on silhouette projection model (SM) in the first time. In the second time, the proposed descriptor is merged with the best existing ones in order to enhance the classification performances. Despite that age classification using gait is a very challenging task, experiments conducted on OU-ISIR database show that their proposed descriptors fusion approach enhances considerably the recognition rate.

Inspec keywords: feature extraction; computer vision; image classification; visual databases; image fusion; cameras; age issues; gait analysis

Other keywords: classification performances; descriptors cascade; silhouette projection model; camera; computer vision community; gait analysis; descriptors fusion approach; nonintrusive biometric; automatic age classification; age estimation; SM; silhouette descriptors; contour descriptors; OU-ISIR database; gait features fusion

Subjects: Image recognition; Computer vision and image processing techniques; Sensor fusion

References

    1. 1)
      • 37. Bobick, A.F., Johnson, A.Y.: ‘Gait recognition using static activity-specific parameters’. Proc. Int. Conf. Computer Vision and Pattern Recognition, Kauai, HI, USA, December 2001, pp. 423–430.
    2. 2)
      • 10. Seralkhatem, A., Osman, A., Sagayan, V., et al: ‘Age-invariant face recognition system using combined shape and texture features’, IET Biometrics, 2015, 4, (2), pp. 98–115.
    3. 3)
      • 43. Liu, Y., Robert, T.C., Tsin, Y.: ‘Gait sequence analysis using frieze patterns’. Proc. European Conf. Computer Vision, Copenhagen, Denmark, May 2002, pp. 657–671.
    4. 4)
      • 28. Li, X., Maybank, S., Yan, S., et al: ‘Gait components and their application to gender recognition’, Trans. Syst. Man Cybern. C, 2008, 38, pp. 145–155.
    5. 5)
      • 16. Lapszo, J., Giovanis, V., Prusik, K., et al: ‘Balance control contributors – the relationships between leg strength and balance control ability in seniors’, Acta Bioeng. Biomech., 2012, 14, (3), pp. 3–8.
    6. 6)
      • 3. Lee, L., Grimson, W.: ‘Gait analysis for recognition and classification’. Proc. Int. Conf. Automatic Face and Gesture Recognition, Washington, USA, May 2002, pp. 155–161.
    7. 7)
      • 2. Lu, J., Tan, Y.P.: ‘Gait-based human age estimation’. Proc. Int. Conf. Acoustics, Speech and Signal Processing, Dallas, TX, USA, March 2010, pp. 1718–1721.
    8. 8)
      • 49. Mansouri, N., Aouled Issa, M., Ben Jemaa, Y.: ‘Gait-based human age classification using a silhouette model’, IET Biometrics, 2017, DOI: 10.1049/iet-bmt.2016.0176.
    9. 9)
      • 35. Ran, Y., Weiss, I., Zheng, Q., et al: ‘Pedestrian detection via periodic motion analysis’, Int. J. Comput. Vis., 2007, 2, pp. 143–160.
    10. 10)
      • 22. Yongxin, G., Lu, J., Wu, F., et al: ‘Age estimation from human body images’. IEEE Int. Conf. Acoustics, Speech and Signal Processing, Vancouver, BC, Canada, March 2013, pp. 2337–2341.
    11. 11)
      • 9. Choi, S.E., Lee, Y.J., Lee, S.J., et al: ‘Age estimation using a hierarchical classifier based on global and local facial features’, Pattern Recognit., 2011, 44, (6), pp. 1262–1281.
    12. 12)
      • 19. Makihara, Y., Mannami, H., Yagi, Y.: ‘Gait analysis of gender and age using a large-scale multi-view gait database’. Proc, Asian Conf. Computer Vision, Queenstown, New Zealand, November 2010, pp. 440–451.
    13. 13)
      • 17. Pietraszewski, B., Winiarski, S., Jaroszczuk, S.: ‘Three dimensional human gait pattern–reference data for normal men’, Acta Bioeng. Biomech., 2012, 14, (3), pp. 9–16.
    14. 14)
      • 32. Nixon, M.S., Tan, T.N., Chellappa, R: ‘Human identification based on gait’, inSpringer (Ed.): ‘International Series on Biometrics’, vol. 1 (Springer-Verlag, 2005).
    15. 15)
      • 36. Yam, C.Y., Nixon, M.S., Carter, J.N.: ‘Gait recognition by walking and running: a model-based approach’. Proc. Asian Conf. Computer Vision, Melbourne, Australia, January 2002, pp. 1–6.
    16. 16)
      • 45. Giaquinto, S., Ciotolaa, E., Margutti, F.: ‘Gait in the water: a comparison between young and elderly subjects’, Disabil. Rehabil., 2007, 29, (9), pp. 727–730.
    17. 17)
      • 8. Chang, K.Y., Chen, C.S.: ‘A learning framework for age rank estimation based on face images with scattering transform’, IEEE Trans. Image Process., 2015, 24, (3), pp. 785–798.
    18. 18)
      • 48. Avineria, E., Shinarb, D., Susiloa, Y.O.: ‘Pedestrians’ behaviour in cross walks: the effects of fear of falling and age’, Accid. Anal. Prev., 2012, 44, (1), pp. 30–34.
    19. 19)
      • 15. Choi, J.S., Kang, D.W., Shin, Y.H., et al: ‘Differences in gait pattern between the elderly and the young during level walking under low illumination’, Acta Bioeng. Biomech., 2014, 16, (1), pp. 3–9.
    20. 20)
      • 4. Wu, T., Turaga, P., Chellappa, R.: ‘Age estimation and face verification across aging using landmarks’, IEEE Trans. Inf. Forensics Sec., 2012, 7, (6), pp. 1780–1788.
    21. 21)
      • 41. BenAbdelkader, C.H., Ross, G.C., Larry, S.D.: ‘Gait recognition using image self-similarity’, EURASIP J. Appl. Signal Process., 2004, 4, pp. 572–585.
    22. 22)
      • 30. Han, J., Bhanu, B.: ‘Individual recognition using gait energy image’, Trans. Pattern Anal. Mach. Intell., 2006, 28, (2), pp. 316–322.
    23. 23)
      • 39. Kim, D., Kim, D., Paik, J.: ‘Gait recognition using active shape model and motion prediction’, IET Comput. Vis., 2010, 4, (1), pp. 25–36.
    24. 24)
      • 29. Yu, S., Tan, T., Huang, K., et al: ‘A study on gait-based gender classification’, IEEE Trans. Image Process., 2009, 18, (8), pp. 1905–1910.
    25. 25)
      • 50. Cuntoor, N., Kale, A., Chellappa, R.: ‘Combining multiple evidences for gait recognition’. Proc. Int. Conf. Acoustics, Speech, and Signal Processing, Hong Kong, April 2003, pp. 33–36.
    26. 26)
      • 21. Iwama, H., Okumura, M., Makihara, Y., et al: ‘The OU-ISIR gait database comprising the large population dataset and performance evaluation of gait recognition’, Trans. Inf. Forensics Sec., 2012, 7, (5), pp. 1511–1521.
    27. 27)
      • 14. Zhang, D., Wang, Y., Bhanu, B.: ‘Age classification based on gait using HMM’. Int. Conf. Computer Society, Istanbul-Turkey, August 2010, pp. 3834–3837.
    28. 28)
      • 42. Daoliang, T., Kaiqi, H., Shiqi, Y., et al: ‘Uniprojective features for gait recognition’, Adv. BiometricsSer. Lect. Notes Comput. Sci., 2007, 46, (42), pp. 673–682.
    29. 29)
      • 33. Sarkar, S., Phillips, J., Liu, Z., et al: ‘The humanID gait challenge problem: data sets, performance, and analysis’, Trans. Pattern Anal. Mach. Intell., 2005, 27, (2), pp. 162–177.
    30. 30)
      • 20. Makihara, Y., Okumura, M., Iwama, H., et al: ‘Gait-based age estimation using a whole-generation gait database’. Proc. Int. Joint Conf. Biometrics, Washington, DC, USA, October 2011, pp. 1–6.
    31. 31)
      • 1. Sarah, N.K.: ‘Using artificial neural network for human age estimation based on facial images’. Proc. Int. Conf. Innovations in Information Technology, Abu Dhabi, UAE, March 2012, pp. 215–219.
    32. 32)
      • 23. Hu, M., Wang, Y., Zhang, Z.: ‘Maximisation of mutual information for gait-based soft biometric classification using gabor features’, IET Biometrics, 2012, 1, (1), pp. 55–62.
    33. 33)
      • 27. Huang, G., Wang, Y.: ‘Gender classification based on fusion of multi-view gait sequences’. Proc. Asian Conf. Computer Vision, Tokyo-Japan, September 2007, pp. 462–471.
    34. 34)
      • 44. Benz, K., Yeo, Ch., Tee, C., et al: ‘A preliminary study of gait-based age estimation techniques’. Proc. APSIPA Annual Summit and Conf., Hong Kong, December 2015, pp. 800–806.
    35. 35)
      • 38. Derbel, A., Mansouri, N., Ben Jemaa, Y., et al: ‘Comparative study between spatio/temporal descriptors for pedestrians recognition by gait’. Proc. Int. Conf. Image Analysis and Recognition, Póvoa de Varzim, Portugal, June 2013, pp. 35–42.
    36. 36)
      • 7. Hong, L.J., Wen, D., Fang, C., et al: ‘Face age estimation by using bisection search tree’. Proc. Int. Conf. Machine Learning and Cybernetics, Tianjin, China, July 2013, pp. 370–374.
    37. 37)
      • 5. Cootes, T.F., Edwards, G.J., Taylor, C.J.: ‘Active appearance models’. Proc. European Conf. Computer Vision, Freiburg-Germany, June 1998, pp. 484–498.
    38. 38)
      • 24. Lu, J., Tan, Y.P.: ‘Ordinary preserving manifold analysis for human age and head pose estimation’, IEEE Trans. Hum.-Mach. Syst., 2013, 43, (2), pp. 249–258.
    39. 39)
      • 47. Byrne, J., Stergiou, N., Blanke, D., et al: ‘Comparison of gait patterns between young and elderly women: an examination of coordination’, Percept. Mot. Skills, 2002, 94, (1), pp. 265–280.
    40. 40)
      • 26. Boulgouris, N., Chi, Z.: ‘Human gait recognition based on matching of body components’, Pattern Recognit., 2007, 40, (6), pp. 1763–1770.
    41. 41)
      • 31. Makihara, Y., Sagawa, R., Mukaigawa, Y., et al: ‘Gait recognition using a view transformation model in the frequency domain’. Proc. European Conf. Computer Vision, Graz, Austria, May 2006, pp. 151–163.
    42. 42)
      • 6. Song, Z., Bingbing, N., Guo, D., et al: ‘Learning universal multi-view age estimator using video context’. Proc. Int. Conf. Computer Vision, Barcelona, Span, November 2011, pp. 241–248.
    43. 43)
      • 13. Ostrosky, K.M., Van Swearingen, J.M., Burdett, R.G., et al: ‘A comparison of gait characteristics in young and old subjects’, Phys. Ther., 1994, 74, (7), pp. 637–644.
    44. 44)
      • 34. Nixon, M.S., Tan, T.N., Chellappa, R.: ‘Human identification based on gait’ (Springer Science and Business Media, 2010).
    45. 45)
      • 25. Jiwen, L., Yap-Peng, T.: ‘Gait-based human age estimation’, IEEE Trans. Inf. Forensics Sec., 2010, 5, (4), pp. 761–770.
    46. 46)
      • 46. Briani, R.V., Taborda, B., Martines, É.C.C., et al: ‘Comparison of temporal and kinetic walking parameters among young people and falling and non-falling elderly persons’, Rev. Bras. Geriatria Gerontol., 2015, 18, (4), pp. 761–768.
    47. 47)
      • 11. Blanke, D., Hageman, P.A.: ‘Comparison of gait of young men and elderly men’, Phys. Ther., 1989, 69, (2), pp. 144–148.
    48. 48)
      • 12. Brandt, T: ‘Vertigo: its multisensory syndromes’ (Springer, 2002), pp. 386–387.
    49. 49)
      • 40. Bashir, K., Xiang, T., Gong, S.: ‘Feature selection on gait energy image for human identification’. Proc. Int. Conf. Acoustics, Speech and Signal Processing, Las Vegas, USA, April 2008, pp. 985–988.
    50. 50)
      • 18. Edson, J.R., Justino, F., Bortolozzi, R.S.: ‘A comparison of SVM and HMM classifiers in the off-line signature verification’, Pattern Recognit. Lett., 2005, 26, (9), pp. 1377–1385.
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-cvi.2017.0055
Loading

Related content

content/journals/10.1049/iet-cvi.2017.0055
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading