access icon free Fuzzy integrals for combining multiple SVM and histogram features for writer's gender prediction

© The Institution of Engineering and Technology
Received 13/08/2016, Accepted 30/03/2017, Revised 15/03/2017, Published 05/04/2017

This study addresses automatic prediction of the writer's gender. We propose the use of fuzzy integral (FI) operators to combine support vector machines (SVMs) associated with different local features. Presently, we focus on local histogram-based features that describe different kinds of handwriting traits to ensure SVM complementarity. First, we introduce a new feature based on the histogram of templates that aims to highlight local orientations of the text strokes. As a second feature, we propose the rotation invariant uniform local binary patterns to enhance local textural information, whereas the third feature is the gradient local binary patterns. Various forms of the FI are used for combining these predictors. Experiments are conducted on four standard datasets of English, Arabic and French handwritten text. First, for each language, the prediction task is evaluated by considering text-independent and writer-independent design. Then, a more challenging prediction is tried by adding the language-independency constraint. The results obtained confirm the effectiveness of the proposed features. Also, they highlight the contribution of the combination step to achieve a robust prediction.

Inspec keywords: support vector machines; text analysis; fuzzy set theory; gradient methods

Other keywords: writer-independent design; local orientations; text strokes; multiple SVM; standard datasets; histogram features; templates; support vector machines complementarity; gradient local binary patterns; handwriting traits; writer gender prediction; text-independent design; FI; fuzzy integral operators; Arabic handwritten text; French handwritten text; language-independency constraint; English handwritten text; rotation invariant uniform local binary patterns; local textural information enhancement; local features

Subjects: Optimisation techniques; Combinatorial mathematics; Document processing and analysis techniques; Knowledge engineering techniques

References

    1. 1)
      • 17. Akbari, Y., Nouri, K., Sadri, J., et al: ‘Wavelet-based gender detection on off-line handwritten documents using probabilistic finite state automata’, Image Vis. Comput., 2017, 59, pp. 17–30.
    2. 2)
      • 31. Burges, C.J.C.: ‘A tutorial on support vector machines for pattern recognition’, Data Min. Knowl. Discov., 1998, 2, (2), pp. 121–167.
    3. 3)
      • 18. Bouadjenek, N., Nemmour, H., Chibani, Y.: ‘Robust soft-biometrics prediction from off-line handwriting analysis’, Appl. Soft Comput., 2016, 46, pp. 980–990.
    4. 4)
      • 23. Cho, S.B., Kim, J.H.: ‘Combining multiple neural networks by fuzzy integral for robust classification’, IEEE Trans. Syst. Man Cybern., 1995, 25, (2), pp. 380–384.
    5. 5)
      • 29. Ferrer, M.A., Vargas, J.F., Morales, A., et al: ‘Robusteness of offline signature verification based on gray level features’, IEEE Trans. Inf. Forensics Sec., 2012, 7, (3), pp. 966–977.
    6. 6)
      • 9. Beech, J.R., Mackintosh, I.C.: ‘Do differences in sex hormones affect handwriting style? Evidence from digit ratio and sex role identity as determinants of the sex of handwriting?’, Pers. Individual Differ., 2005, 39, pp. 459–468.
    7. 7)
      • 24. Cho, S.B.: ‘Fuzzy aggregation of modular neural networks with ordered weighted averaging operators’, Int. J. Approx. Reason., 1995, 13, (4), pp. 359–375.
    8. 8)
      • 5. Dorfberger, S., Adi-Japha, E., Karni, A.: ‘Sex differences in motor performance and motor learning in children and adolescents: an increasing male advantage in motor learning and consolidation phase gains’, Behav. Brain Res., 2009, 198, (1), pp. 165–171.
    9. 9)
      • 3. 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.
    10. 10)
      • 13. Bouadjenek, N., Nemmour, H., Chibani, Y.: ‘Age, gender and handedness prediction from handwriting using gradient features’. Proc. Int. Conf. Document Analysis and Recognition (ICDAR), Tunisia, August 2015, pp. 1116–1120.
    11. 11)
      • 19. Liwicki, M., Schlapbach, A., Bunke, H.: ‘Automatic gender detection using on-line and off-line information’, Pattern Anal. Appl., 2011, 14, pp. 87–92.
    12. 12)
      • 8. Collins, R.E.: ‘The effect of gender on violent and non-violent recidivism: a meta-analysis’, J. Criminal Justice, 2010, 38, (4), pp. 675–684.
    13. 13)
      • 28. Osman Ali, A.S., Sagayan, V., Saeed, A.M., et al: ‘Age-invariant face recognition system using combined shape and texture features’, IET Biometrics, 2015, 4, (2), pp. 98–115.
    14. 14)
      • 32. Nemmour, H., Chibani, Y.: ‘Multiple support vector machines for land cover change detection: an application for mapping urban extensions’, J. Photogramm. Remote Sens., 2006, 61, (2), pp. 125–133.
    15. 15)
      • 15. Bouadjenek, N., Nemmour, H., Chibani, Y.: ‘Histogram of oriented gradients for writer's gender, handedness and age prediction’. Proc. Int. Conf. Innovations in Intelligent Systems and Applications (INISTA), Madrid, Spain, September 2015, pp. 220–224.
    16. 16)
      • 27. Ojala, T., Pietikainen, M., Harwood, D.: ‘A comparative study of texture measures with classification based on featured distributions’, Pattern Recognit., 1996, 29, (1), pp. 51–59.
    17. 17)
      • 2. Costa-Abreu, M.D., Fairhurst, M.: ‘Improving handwritten signature-based identity prediction through the integration of fuzzy soft-biometric data’. Proc. Int. Conf. Frontiers in Handwriting Recognition (ICFHR), Bari, Italy, September 2012, pp. 797–802.
    18. 18)
      • 10. Cha, S.H., Srihari, S.N.: ‘A priori algorithm for sub-category classification analysis of handwriting’. Proc. Int. Conf. Document Analysis and Recognition (ICDAR), Seattle, USA, September 2001, pp. 1022–1025.
    19. 19)
      • 7. Bennett, S., Farrington, D.P., Huesmann, L.R.: ‘Explaining gender differences in crime and violence: the importance of social cognitive skills’, Aggression Violent Behav., 2005, 10, (3), pp. 263–288.
    20. 20)
      • 33. Mahmoud, S.A., Ahmad, I., Al-Khatib, W.G., et al: ‘KHATT: Arabic offline handwritten text database’. Proc. Int. Conf. Frontiers in Handwriting Recognition (ICFHR), Seattle, USA, 2012, pp. 449–454.
    21. 21)
      • 6. Voyer, D.: ‘Sex differences in dichotic listening’, Brain Cogn. J., 2011, 76, pp. 245–255.
    22. 22)
      • 16. Siddiqi, I., Djeddi, C., Raza, A., et al: ‘Automatic analysis of handwriting for gender classification’, Pattern Anal. Appl., 2014, 18, pp. 887–899.
    23. 23)
      • 34. Djeddi, C., Gattal, A., Souici-Meslati, L., et al: ‘LAMIS-MSHD: a multi-script offline handwriting database’. Proc. Int. Conf. Frontiers in Handwriting Recognition (ICFHR), Heraklion, Greece, September 2014, pp. 93–97.
    24. 24)
      • 22. Serdouk, Y., Nemmour, H., Chibani, Y.: ‘New off-line handwritten signature verification method based on artificial immune recognition system’, Expert Syst. Appl., 2016, 51, pp. 186–194.
    25. 25)
      • 26. Tang, S., Goto, S.: ‘Histogram of template for human detection’. Proc. Int. Conf. Acoustics Speech and Signal Processing (ICASSP), Dallas, TX, March 2010, pp. 2186–2189.
    26. 26)
      • 35. Bouadjenek, N., Nemmour, H., Chibani, Y.: ‘Fuzzy integral for combining SVM-based handwritten soft-biometrics prediction’. Workshop on Document Analysis Systems (DAS), Santorini, Greece, April 2016, pp. 311–316.
    27. 27)
      • 14. Bouadjenek, N., Nemmour, H., Chibani, Y.: ‘Local descriptors to improve off-line handwriting-based gender prediction’. Proc. Int. Conf. Soft Computing and Pattern Recognition (SoCPaR), Tunisia, August 2014, pp. 43–47.
    28. 28)
      • 12. Al-Maadeed, S., Hassaine, A.: ‘Automatic prediction of age, gender, and nationality in offline handwriting’, EURASIP J. Image Video Process., 2014, 10, pp. 1–10.
    29. 29)
      • 1. Bandi, K.R., Srihari, S.N.: ‘Writer demographic classification using bagging and boosting’. Proc. Int. Conf. Graphonomics Society, Salerno, Italy, 2005, pp. 133–137.
    30. 30)
      • 20. Djeddi, C., Al-Maadeed, S., Gattal, A., et al: ‘ICDAR 2015 competition on multi-script writer identification and gender classification using ‘QUWI’ database’. Proc. Int. Conf. Document Analysis and Recognition (ICDAR), Tunisia, August 2015, pp. 1191–1195.
    31. 31)
      • 4. Shulman, L.M.: ‘Gender differences in Parkinson's disease’, Gender Med., 2007, 4, (1), pp. 8–18.
    32. 32)
      • 25. Verikas, A., Lipnickas, A., Malmqvist, K., et al: ‘Soft combination of neural classifiers: a comparative study’, Pattern Recognit. Lett., 1999, 20, (4), pp. 429–444.
    33. 33)
      • 30. Vapnik, V.N.: ‘The nature of statistical learning theory’ (Springer-Verlag New York, Inc., NY, USA, 1995).
    34. 34)
      • 21. Djeddi, C., Al-Maadeed, S., Gattal, A., et al: ‘ICFHR 2016 competition on multi-script writer demographics classification using ‘QUWI’ database’. Proc. Int. Conf. Frontiers in Handwriting Recognition (ICFHR), Shenzhen, China, October 2016, pp. 602–606.
    35. 35)
      • 11. Liwicki, M., Schlapbach, A., Loretan, P., et al: ‘Automatic detection of gender and handedness from on-line handwriting’. Proc. Int. Conf. Graphonomics Society, Melbourne, Australia, 2007, pp. 179–183.
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-bmt.2016.0140
Loading

Related content

content/journals/10.1049/iet-bmt.2016.0140
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading