access icon free Gender classification based on fuzzy clustering and principal component analysis

Gender classification is one of the most challenging problems in computer vision. Facial gender detection of neonates and children is also known as a highly demanding issue for human observers. This study proposes a novel gender classification method using frontal facial images of people. The proposed approach employs principal component analysis (PCA) and fuzzy clustering technique, respectively, for feature extraction and classification steps. In other words, PCA is applied to extract the most appropriate features from images as well as reducing the dimensionality of data. The extracted features are then used to assign the new images to appropriate classes – male or female – based on fuzzy clustering. The computational time and accuracy of the proposed method are examined together and the prominence of the proposed approach compared to most of the other well-known competing methods is proved, especially for younger faces. Experimental results indicate the considerable classification accuracies which have been acquired for FG-Net, Stanford and FERET databases. Meanwhile, since the proposed algorithm is relatively straightforward, its computational time is reasonable and often less than the other state-of-the-art gender classification methods.

Inspec keywords: data reduction; image classification; face recognition; principal component analysis; feature extraction; fuzzy set theory; gender issues; pattern clustering

Other keywords: data dimensionality reduction; Stanford database; FERET database; frontal facial images; PCA; computer vision; facial gender detection; fuzzy clustering technique; feature extraction step; gender classification method; computational time; feature classification step; principal component analysis; FG-Net database

Subjects: Computer vision and image processing techniques; Combinatorial mathematics; Data handling techniques; Other topics in statistics; Image recognition; Combinatorial mathematics; Other topics in statistics

References

    1. 1)
      • 8. Leng, X.M., Wang, Y.: ‘Improving generalization for gender classification’. 15th IEEE Int. Conf. on Image Processing (ICIP), San Diego, USA, October 2008, pp. 16561659.
    2. 2)
      • 5. Guo, G.-D., Dyer, C., Fu, Y., et al: ‘Is gender recognition influenced by age?’. IEEE Int. Workshop on Human-Computer Interaction (HCI'09), 2009, pp. 169178.
    3. 3)
      • 18. Bhattacharya, M., Das, A.: ‘Fuzzy logic based segmentation of microcalcification in breast using digital mammograms considering multiresolution’. Int. Machine Vision and Image Processing Conf., 2007, pp. 98105.
    4. 4)
      • 29. Mehmood, Y., Ishtiaq, M., Tariq, M. : ‘Classifier ensemble optimization for gender classification using genetic algorithm’. IEEE Int. Conf. on Information and Emerging Technology, Karachi, Pakistan, June 2010, pp. 15.
    5. 5)
      • 22. Ekenel, H.K., Stiefelhagen, R.: ‘Two-class linear discriminant analysis for face recognition’. 15th IEEE Conf. on Signal Processing and Communications Applications, June 2007, pp. 1113.
    6. 6)
      • 6. Golomb, B.A., Lawrence, D.T., Sejnowski, T.J.: ‘Advances in neural information processing systems’. SEXNET: A Neural Network Identifies Sex from Human Faces, 1991, pp. 572577.
    7. 7)
      • 10. Nazir, M., Ishtiaq, M., Batool, A., et al: ‘Feature selection for efficient gender classification’. 11th WSEAS Int. Conf. on Fuzzy Systems, 2010, pp. 7075.
    8. 8)
    9. 9)
      • 4. Hassanpour, H., Dehghan, H.: ‘Neonate facial gender classification using PCA and fuzzy clustering’. 17th Iranian Conf. of Biomedical Engineering, Isfahan, Iran, November 2010, pp. 15.
    10. 10)
      • 17. Rodarmel, C., Shan, J.: ‘Principal component analysis for hyperspectral image classification’, Surv. Land Inf. Syst., 2002, 62, (2), pp. 115122.
    11. 11)
      • 11. Wang, Y., Ricanek, K.: ‘Gender classification from infants to seniors’. Fourth IEEE Int. Conf. on Biometrics: Theory Applications and Systems, Washington DC, USA, 2010, pp. 16.
    12. 12)
      • 27. FERET Database, Available from: http://www.itl.nist.gov/iad/humanid/feret/, accessed 2004.
    13. 13)
      • 24. Rajan, B.K., Anto, N., Jose, S.: ‘Fusion of iris & fingerprint biometrics for gender classification using neural network’. Second Int. Conf. on Current Trends in Engineering and Technology (ICCTET), July 2014, pp. 216221.
    14. 14)
    15. 15)
    16. 16)
      • 19. Balafar, M.A., Ramli, A.R., Saripan, M.I., et al: ‘New multi-scale medical image segmentation based on fuzzy C-mean (FCM)’. The 2008 IEEE Conf. on Innovative Technologies in Intelligent Systems and Industrial Applications, 2008, pp. 6670.
    17. 17)
      • 7. Gutta, S., Wechsler, H., Phillips, P.J.: ‘Gender and ethnic classification of face images’. Proc. Third IEEE Int. Conf. on Automatic Face and Gesture Recognition, 1998, pp. 194199.
    18. 18)
    19. 19)
    20. 20)
    21. 21)
      • 9. Rai, P., Khanna, P.: ‘Gender classification using radon and wavelet transforms’. Fifth IEEE Int. Conf. on Industrial and Information Systems, Mangalore, India, 2010, pp. 448451.
    22. 22)
      • 16. Zheng, W.: ‘A novel improvement to PCA for image classification’. Int. Conf. on Computer Science and Service System (CSSS), 2011, pp. 19641967.
    23. 23)
    24. 24)
    25. 25)
      • 20. Fg-net aging database. http://www.fgnet.rsunit.com, accessed 2010.
    26. 26)
    27. 27)
      • 31. Sun, Z., Bebis, G., Yuan, X., et al: ‘Genetic feature subset selection for gender classification: a comparison study’. IEEE Proc. on Applications of Computer Vision, 2002, pp. 165170.
    28. 28)
      • 15. Bajwa, I.S., Hyder, S.: ‘PCA based image classification of single-layered cloud types’, J. Market Forces, 2005, 1, (2), pp. 313.
    29. 29)
      • 12. Kekre, H.B., Thepade, S.D., Chopra, T.: ‘Face and gender recognition using principal component analysis’, Int. J. Comput. Sci. Eng., 2010, 2, (4), pp. 959964.
    30. 30)
      • 13. Akbari, R., Mozaffari, S.: ‘Performance enhancement of PCA-based face recognition system via gender classification method’. 6th Iranian Machine Vision and Image Processing Conf. (MVIP), Isfahan, Iran, October 2010, pp. 16.
    31. 31)
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-cvi.2015.0041
Loading

Related content

content/journals/10.1049/iet-cvi.2015.0041
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading