access icon free Label propagation approach for predicting missing biographic labels in face-based biometric records

A biometric system uses the physical or behavioural attributes of a person, such as face, fingerprint, iris or voice, to recognise an individual. Many operational biometric systems store the biographic information of an individual, viz., name, gender, age and ethnicity, besides the biometric data itself. Thus, the biometric record pertaining to an individual consists of both biometric data and biographic data. We propose the use of a graph structure to model the relationship between the biometric records in a database. We show the benefits of such a graph in deducing biographic labels of incomplete records, i.e. records that may have missing biographic information. In particular, we use a label propagation scheme to deduce missing values for both binary-valued biographic attributes (e.g. gender) as well as multi-valued biographic attributes (e.g. age group). Experimental results using face-based biometric records consisting of name, age, gender and ethnicity convey the pros and cons of the proposed method.

Inspec keywords: graph theory; face recognition; biometrics (access control); visual databases; records management

Other keywords: behavioural attributes; predicting missing biographic labels; biographic information; physical attributes; face based biometric records; operational biometric systems; graph theory; label propagation approach

Subjects: Image recognition; Spatial and pictorial databases; Computer vision and image processing techniques; Combinatorial mathematics; Combinatorial mathematics

References

    1. 1)
      • 42. Michael, J.: ‘40,000 namen. anredebestimmung anhand des vornamens’. c't, 2007, pp. 182183.
    2. 2)
      • 31. Ratha, N.K., Connell, J.H., Pankanti, S.: ‘Big data approach to biometric-based identity analytics’, IBM J. Res. Dev., 2015, 59, (2/3), pp. 4:14:11.
    3. 3)
      • 16. Han, H., Otto, C., Liu, X., et al: ‘Demographic estimation from face images: human vs. machine performance’, IEEE Trans. Pattern Anal. Mach. Intell., 2015, 37, (6), pp. 11481161.
    4. 4)
      • 25. Klare, B.F., Burge, M.J., Klontz, J.C., et al: ‘Face recognition performance: role of demographic information’, IEEE Trans. Inf. Forensics Sec., 2012, 7, (6), pp. 17891801.
    5. 5)
      • 19. Ding, H., Huang, D., Wang, Y., et al: ‘Facial ethnicity classification based on boosted local texture and shape descriptions’. IEEE Int. Conf. and Workshops on Automatic Face and Gesture Recognition, 2013, pp. 16.
    6. 6)
      • 17. Chen, J.-C., Kumar, A., Ranjan, R., et al: ‘A cascaded convolutional neural network for age estimation of unconstrained faces’. Conf. on Biometrics Theory, Applications and Systems (BTAS), 2016, pp. 18.
    7. 7)
      • 29. Bhatt, H.S., Singh, R., Vatsa, M.: ‘Can combining demographics and biometrics improve de-duplication performance?IEEE Computer Society Conf. on Computer Vision and Pattern Recognition Workshops, 2013, pp. 188193.
    8. 8)
      • 27. Jain, A.K., Nandakumar, K., Lu, X., et al: ‘Integrating faces, fingerprints, and soft biometric traits for user recognition’. Workshop on Biometric Authentication, 2004, pp. 259269.
    9. 9)
      • 10. Chen, H., Gallagher, A.C., Girod, B.: ‘What's in a name?’. IEEE Conf. on Computer Vision and Pattern Recognition, 2013, vol. 6, pp. 33663373.
    10. 10)
      • 46. Wilcoxon, F.: ‘Individual comparisons by ranking methods’, Biometrics Bull., 1945, 1, (6), pp. 8083.
    11. 11)
      • 21. Muhammad, G., Hussain, M., Alenezy, F., et al: ‘Race classification from face images using local descriptors’, Int. J. Artif. Intell. Tools, 2012, 21, (05), p. 1250019.
    12. 12)
      • 15. Makinen, E., Raisamo, R.: ‘Evaluation of gender classification methods with automatically detected and aligned faces’, IEEE Trans. Pattern Anal. Mach. Intell., 2008, 30, (3), pp. 541547.
    13. 13)
      • 45. Huang, G.B., Ramesh, M., Berg, T., et al: ‘Labeled faces in the wild: a database for studying face recognition in unconstrained environments’. University of Massachusetts, Amherst, Technical Report 07-49, October 2007.
    14. 14)
      • 7. Almudhahka, N.Y., Nixon, M.S., Hare, J.S.: ‘Unconstrained human identification using comparative facial soft biometrics’. 2016 IEEE 8th Int. Conf. on Biometrics Theory, Applications and Systems (BTAS), 2016, pp. 16.
    15. 15)
      • 9. Chu, W.-T., Chiu, C.-H.: ‘Predicting occupation from single facial images’. IEEE Int. Symp. on Multimedia (ISM), 2014, pp. 912.
    16. 16)
      • 35. Rubinstein, M., Liu, C., Freeman, W.T.: ‘Annotation propagation in large image databases via dense image correspondence’. European Conf. on Computer Vision, 2012, pp. 8599.
    17. 17)
      • 14. Levi, G., Hassncer, T.: ‘Age and gender classification using convolutional neural networks’. IEEE Conf. on Computer Vision and Pattern Recognition Workshops (CVPRW), 2015, pp. 3442.
    18. 18)
      • 3. Ricanek, K., Tesafaye, T.: ‘Morph: a longitudinal image database of normal adult age-progression’. IEEE Conf. on Automatic Face and Gesture Recognition, 2006, pp. 341345.
    19. 19)
      • 20. Kumar, N., Berg, A., Belhumeur, P.N., et al: ‘Describable visual attributes for face verification and image search’, IEEE Trans. Pattern Anal. Mach. Intell., 2011, 33, (10), pp. 19621977.
    20. 20)
      • 34. Zhou, D., Bousquet, O., Lal, T.N., et alLearning with local and global consistency’. Advances in Neural Information Processing Systems (NIPS), 2003, vol. 16, pp. 321328.
    21. 21)
      • 11. Dantcheva, A., Elia, P., Ross, A.: ‘What else does your biometric data reveal? A survey on soft biometrics’, IEEE Trans. Inf. Forensics Sec., 2016, 11, (3), pp. 441467.
    22. 22)
      • 41. Skerry, P.: ‘Counting on the census?: Race, group identity, and the evasion of politics’, vol. 56 (Brookings Institution Press, 2000).
    23. 23)
      • 8. Martinho-Corbishley, D., Nixon, M.S., Carter, J.N.: ‘Soft biometric retrieval to describe and identify surveillance images’. ISBA 2016 – IEEE Int. Conf. on Identity, Security and Behavior Analysis, 2016, pp. 16.
    24. 24)
      • 37. Yu, J., Jin, X., Han, J., et al: ‘Collection-based sparse label propagation and its application on social group suggestion from photos’, ACM Trans. Intell. Syst. Technol., 2011, 2, (2), pp. 12:112:21.
    25. 25)
      • 28. Tyagi, V., Karanam, H.P.: ‘Fusing biographical and biometric classifiers for improved person identification’. Conf. on Pattern Recognition (ICPR), 2012, pp. 23512354.
    26. 26)
      • 4. Swearingen, T., Ross, A.: ‘Predicting missing demographic information in biometric records using label propagation techniques’. Conf. of the Biometrics Special Interest Group (BIOSIG), 2016, pp. 15.
    27. 27)
      • 32. ‘Think BIG Fusion of Biometric and Biographic Data In Large-Scale Identification Projects’. WCC Smart Search & Match, Technical Report.
    28. 28)
      • 23. Fu, S., He, H., Hou, Z.-G.: ‘Race classification from face: a survey’, IEEE Trans. Pattern Anal. Mach. Intell., 2014, 36, (12), pp. 24832509.
    29. 29)
      • 43. Frequently occuring first names and surnames from the 1990 census’, United States Census Bureau, Technical Report, 1995.
    30. 30)
      • 33. Liu, W., Ruths, D.: ‘What's in a name? Using first names as features for gender inference in twitter’. Analyzing Microtext: Papers from the 2013 AAAI Spring Symp., 2013, pp. 1016.
    31. 31)
      • 44. Word, D.L., Coleman, C.D., Nunziata, R., et al: ‘Demographic aspects of surnames from Census 2000’. United States Census Bureau, Technical Report, 2000.
    32. 32)
      • 30. Sudhish, P.S., Jain, A.K., Cao, K.: ‘Adaptive fusion of biometric and biographic information for identity deduplication’, Pattern Recognit. Lett., 2016, 84, pp. 199207.
    33. 33)
      • 6. Almudhahka, N., Nixon, M., Hare, J.: ‘Human face identification via comparative soft biometrics’. ISBA 2016 – IEEE Int. Conf. on Identity, Security and Behavior Analysis, 2016, pp. 16.
    34. 34)
      • 39. Tang, J., Li, M., Li, Z., et al: ‘Tag ranking based on salient region graph propagation’, Multimedia Syst., 2015, 21, (3), pp. 267275.
    35. 35)
      • 22. Ambekar, A., Ward, C., Mohammed, J., et al: ‘Name-ethnicity classification from open sources’. ACM SIGKDD Int. Conf. on Knowledge Discovery and Data Mining, 2009, pp. 4958.
    36. 36)
      • 1. Jain, A.K., Ross, A.A., Nandakumar, K.: ‘Introduction to biometrics’ (Springer Science & Business Media, 2011).
    37. 37)
      • 38. Liu, D., Yan, S., Hua, X.S., et al: ‘Image retagging using collaborative tag propagation’, IEEE Trans. Multimedia, 2011, 13, (4), pp. 702712.
    38. 38)
      • 12. Gallagher, A.C., Chen, T.: ‘Estimating age, gender, and identity using first name priors’. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), 2008, pp. 18.
    39. 39)
      • 13. Shan, C.: ‘Learning local binary patterns for gender classification on real-world face images’, Pattern Recognit. Lett., 2012, 33, (4), pp. 431437.
    40. 40)
      • 24. Ross, A.A., Nandakumar, K., Jain, A.A.: ‘Handbook of multibiometrics’, vol. 6 (2006), Springer Science and Business Media.
    41. 41)
      • 36. Houle, M.E., Oria, V., Satoh, S., et al: ‘Annotation propagation in image databases using similarity graphs’, ACM Trans. Multimedia Comput. Commun. Appl., 2013, 27, (1), pp. 288311.
    42. 42)
      • 26. Han, H., Klare, B.F., Bonnen, K., et al: ‘Matching composite sketches to face photos: a component-based approach’, IEEE Trans. Inf. Forensics Sec., 2013, 8, (1), pp. 191204.
    43. 43)
      • 18. Fu, Y., Guo, G., Huang, T.S.: ‘Age synthesis and estimation via faces: a survey’, IEEE Trans. Pattern Anal. Mach. Intell., 2010, 32, (11), pp. 19551976.
    44. 44)
      • 5. Jain, A.K., Dass, S.C., Nandakumar, K.: ‘Can soft biometric traits assist user recognition?’, in Jain, Anil K., Ratha, Nalini K.Defense and security’, vol. 5404 (International Society for Optics and Photonics, 2004), pp. 561572.
    45. 45)
      • 2. Otto, C., Wang, D., Jain, A.: ‘Clustering millions of faces by identity’, IEEE Trans. Pattern Anal. Mach. Intell., 2017.
    46. 46)
      • 40. Mateos, P.: ‘A review of name-based ethnicity classification methods and their potential in population studies’, Popul. Space Place, 2007, 13, (4), pp. 243263.
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-bmt.2017.0117
Loading

Related content

content/journals/10.1049/iet-bmt.2017.0117
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading