Your browser does not support JavaScript!
http://iet.metastore.ingenta.com
1887

access icon free Analysing comparative soft biometrics from crowdsourced annotations

© The Institution of Engineering and Technology
Received 09/12/2015, Accepted 21/03/2016, Revised 23/02/2016, Published 22/04/2016

Soft biometrics enable human description and identification from low-quality surveillance footage. This study premises the design, collection and analysis of a novel crowdsourced dataset of comparative soft biometric body annotations, obtained from a richly diverse set of human annotators. The authors annotate 100 subject images to provide a coherent, in-depth appraisal of the collected annotations and inferred relative labels. The dataset includes gender as a comparative trait and the authors find that comparative labels characteristically contain additional discriminative information over traditional categorical annotations. Using the authors’ pragmatic dataset, semantic recognition is performed by inferring relative biometric signatures using a RankSVM algorithm. This demonstrates a practical scenario, reproducing responses from a video surveillance operator searching for an individual. The approach can reliably return the correct match in the top 7% of results with ten comparisons, or top 13% of results using just five sets of subject comparisons.

Inspec keywords: biometrics (access control); video surveillance; support vector machines

Other keywords: pragmatic dataset; additional discriminative information; RankSVM algorithm; comparative soft biometric analysis; semantic recognition; human identification; video surveillance operator searching; human description; low-quality surveillance footage; comparative soft biometric body annotations; crowdsourced annotations

Subjects: Video signal processing; Knowledge engineering techniques; Data security; Image recognition; Television and video equipment, systems and applications

References

    1. 1)
      • 43. Ng, C.B., Tay, Y.H., Goi, B.: ‘Recognizing human gender in computer vision: a survey’. PRICAI, 2012, pp. 335–346.
    2. 2)
      • 22. Parikh, D., Grauman, K.: ‘Relative attributes’. ICCV, 2011, pp. 503–510.
    3. 3)
      • 20. Lucas, T., Henneberg, M.: ‘Comparing the face to the body, which is better for identification?’, Int. J. Legal Med., 2015, 130, 2, pp. 533–540.
    4. 4)
      • 17. Park, U., Jain, A.K.: ‘Face matching and retrieval using soft biometrics’, IEEE Trans. Inf. Forens. Secur., 2010, 5, (3), pp. 406–415.
    5. 5)
      • 7. Dantcheva, A., Velardo, C., D'angelo, A., et al: ‘Bag of soft biometrics for person identification’, Multim. Tools Appl., 2011, 51, (2), pp. 739–777.
    6. 6)
      • 23. Matthews, T., Nixon, M.S., Niranjan, M.: ‘Enriching texture analysis with semantic data’. CVPR, 2013, pp. 1248–1255.
    7. 7)
      • 44. Denman, S., Fookes, C., Bialkowski, A., et al: ‘Soft-biometrics: unconstrained authentication in a surveillance environment’. DICTA, 2009, pp. 196–203.
    8. 8)
      • 26. Yuille, J.C., Cutshall, J.L.: ‘A case study of eyewitness memory of a crime’, J. Appl. Psychol., 1986, 71, (2), p. 291.
    9. 9)
      • 14. Wang, X., Zhao, R.: ‘Person re-identification: system design and evaluation overview’. Person Re-Identification, 2014, pp. 351–370.
    10. 10)
      • 15. Zhu, J., Liao, S., Yi, D., et al: ‘Multi-label CNN based pedestrian attribute learning for soft biometrics’. ICB, 2015, pp. 535–540.
    11. 11)
      • 40. Zhou, Z., Wang, Y., Teoh, E.K.: ‘A framework for semantic people description in multi-camera surveillance systems’, Image Vis. Comput., 2016, 46, pp. 29–46.
    12. 12)
      • 36. Madadi, M., Escalera, S., Gonz`alez, J., et al: ‘Multi-part body segmentation based on depth maps for soft biometry analysis’, Pattern Recognit. Lett., 2015, 56, pp. 14–21.
    13. 13)
      • 18. Jain, A.K., Dass, S.C., Nandakumar, K.: ‘Can soft biometric traits assist user recognition?’. Defense and Security, 2004, pp. 561–572.
    14. 14)
      • 1. Jain, A.K., Ross, A., Prabhakar, S.: ‘An introduction to biometric recognition’, IEEE Trans. Circuits Syst. Video Technol., 2004, 14, (1), pp. 4–20.
    15. 15)
      • 27. Jaha, E.S., Nixon, M.S.: ‘Viewpoint invariant subject retrieval via soft clothing biometrics’. ICB, 2015, pp. 73–78.
    16. 16)
      • 25. Meissner, C.A., Sporer, S.L., Schooler, J.W.: ‘Person descriptions as eyewitness evidence’. 2007.
    17. 17)
      • 3. Nixon, M.S., Correia, P.L., Nasrollahi, K., et al: ‘On soft biometrics’, Pattern Recognit. Lett., 2015, 68, Pt 2, pp. 218–230.
    18. 18)
      • 16. Adjeroh, D., Cao, D., Piccirilli, M., et al: ‘Predictability and correlation in human metrology’. WIFS, 2010, pp. 1–6.
    19. 19)
      • 46. Joachims, T.: ‘Optimizing search engines using click through data’. SIGKDD, 2002, pp. 133–142.
    20. 20)
      • 34. Layne, R., Timothy Hospedales, M., Gong, S.: ‘Attributes-based re-identification’. Person Re-Identification, 2014, pp. 93–117.
    21. 21)
      • 24. Flin, R.H., Shepherd, J.W.: ‘Tall stories: eyewitnesses’ ability to estimate height and weight characteristics’, Hum. Learn., J. Pract. Res. Appl., 1986, 5, (1), pp. 29–38.
    22. 22)
      • 28. Farenzena, M., Bazzani, L., Perina, A., et al: ‘Person re-identification by symmetry-driven accumulation of local features’. CVPR, 2010, pp. 2360–2367.
    23. 23)
      • 32. Deng, Y., Luo, P., Loy, C., et al: ‘Pedestrian attribute recognition at far distance’. ACMMM, 2014, pp. 789–792.
    24. 24)
      • 21. Reid, D., Samangooei, S., Chen, C., et al: ‘Soft biometrics for surveillance: an overview’. MTAS, 2013, pp. 327–352.
    25. 25)
      • 5. Tome, P., Fierrez, J., Vera-Rodriguez, R., et al: ‘Soft biometrics and their application in person recognition at a distance’, IEEE Trans. Inf. Forens. Secur., 2014, 9, (3), pp. 464–475.
    26. 26)
      • 37. Perlin, H.A., Lopes, H.S.: ‘Extracting human attributes using a convolutional neural network approach’, Pattern Recognit. Lett., 2015, 68, Pt 2, pp. 250–259.
    27. 27)
      • 45. Han, H., Otto, C., Liu, X., et al: ‘Demographic estimation from face images: human vs. machine performance’, TPAMI, 2014, PP, (99), pp. 1148–1161.
    28. 28)
      • 6. Seely, R.D., Samangooei, S., Lee, M., et al: ‘The University of Southampton multi-biometric tunnel and introducing a novel 3d gait dataset’. BTAS, 2008, pp. 1–6.
    29. 29)
      • 10. Vezzani, R., Baltieri, D., Cucchiara, R.: ‘People reidentification in surveillance and forensics: a survey’, ACM Comput. Surv., 2013, 46, (2), p. 29.
    30. 30)
      • 31. Layne, R., Hospedales, T.M., Gong, S., et al: ‘Person re-identification by attributes’. BMVC, 2012, vol. 2, p. 8.
    31. 31)
      • 11. Kuehn, L.L.: ‘Looking down a gun barrel: person perception and violent crime’, Percept. Mot. Skills, 1974, 39, (3), pp. 1159–1164.
    32. 32)
      • 29. Prosser, B., Zheng, W., Gong, S., et al: ‘Person re-identification by support vector ranking’. BMVC, 2010, vol. 2, p. 6.
    33. 33)
      • 4. Reid, D.A., Nixon, M.S., Stevenage, S.V.: ‘Soft biometrics; human identification using comparative descriptions’, IEEE Trans. Pattern Anal. Machine Intell., 2014, 36, (6), pp. 1216–1228.
    34. 34)
      • 2. Dantcheva, A., Elia, P., Ross, A.: ‘What else does your biometric data reveal?’. A survey on soft biometrics, 2015.
    35. 35)
      • 9. MacLeod, M.D., Frowley, J.N., Shepherd, J.W.: ‘Whole body information: its relevance to eyewitnesses’, in Ross, D.F., Read, J.D., Toglia, M.P. (Eds.): ‘Adult eyewitness testimony: current trends and developments’ (Cambridge University Press, 1994), pp. 125–143.
    36. 36)
      • 41. Cao, L., Dikmen, M., Fu, Y., et al: ‘Gender recognition from body’. ACMMM, 2008, pp. 725–728.
    37. 37)
      • 12. Loftus, E.F., Palmer, J.C.: ‘Eyewitness testimony’ (Springer, 1996).
    38. 38)
      • 13. An, L., Chen, X., Kafai, M., et al: ‘Improving person re-identification by soft biometrics based reranking’. ICDSC, 2013, pp. 1–6.
    39. 39)
      • 30. Zheng, W., Gong, S., Xiang, T.: ‘Person re-identification by probabilistic relative distance comparison’. CVPR, 2011, pp. 649–656.
    40. 40)
      • 42. Guo, G., Mu, G., Fu, Y.: ‘Gender from body: a biologically-inspired approach with manifold learning’. ACCV, 2010, pp. 236–245.
    41. 41)
      • 8. Samangooei, S., Guo, B., Nixon, M.S.: ‘The use of semantic human description as a soft biometric’. BTAS, 2008, pp. 1–7.
    42. 42)
      • 38. Arigbabu, O.A., Syed Ahmad, S.M., Adnan, W.A.W., et al: ‘Integration of multiple soft biometrics for human identification’, Pattern Recognit. Lett., 2015, 68, pp. 278–287.
    43. 43)
      • 35. Moctezuma, D., Conde, C., De Diego, I.M., et al: ‘Soft-biometrics evaluation for people re-identification in uncontrolled multi-camera environments’, EURASIP J. Image Video Process., 2015, 2015, (1), pp. 1–20.
    44. 44)
      • 39. Denman, S., Halstead, M., Fookes, C., et al: ‘Searching for people using semantic soft biometric descriptions’, Pattern Recognit. Lett., 2015, 68, pp. 306–315.
    45. 45)
      • 19. Jain, A.K., Nandakumar, K., Lu, X., et al: ‘Integrating faces, fingerprints, and soft biometric traits for user recognition’. Biometric Authentication, 2004, pp. 259–269.
    46. 46)
      • 33. Zhu, J., Liao, S., Lei, Z., et al: ‘Pedestrian attribute classification in surveillance: database and evaluation’. ICCVW, 2013, pp. 331–338.
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-bmt.2015.0118
Loading

Related content

content/journals/10.1049/iet-bmt.2015.0118
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading
Print this page
This is a required field
Please enter a valid email address