A Comparison of Age Prediction Classifiers via Active Appear-Acne Model

  • Abstract
  • Keywords
  • References
  • PDF
  • Abstract

    Individual age gives key demographic data. It is viewed as a paramount delicate biometric characteristic for individual identification, contrasted with other pattern recognition issues. Age estimation is a complex issue particularly in relation to facial pictures with different ages, since the aging procedure varies extraordinarily across different age groups. In this research, we proposed deep learning algorithm for age prediction In light of Active Appearance Models (AAM) and six classifiers: Support Vector Machine (SVM), K-Nearest Neighbor (KNN), Support Vector Regression (SVR), Canonical Correlation Analysis (CCA), Linear Discriminant Analysis (LDA), and Projection Twin Support Vector Machine (PTSVM) to move forward the accuracy of age prediction dependent upon the introduced strategies. In this algorithm, we extracted the features of the facial images in features vectors using AAM model, machine learning algorithms are used to predict the age. We distinguished that the precision of CCA algorithm is the best, the intermediate is SVR and the KNN algorithm is the lowest.



  • Keywords

    Age Prediction, Feature Extraction, Active Appearance Models (AAM), Age Classification.

  • References

      [1] Grd, P., Introduction to human age estimation using face images. Research Papers Faculty of Materials Science and Technology Slovak University of Technology, 2013. 21(Special Issue): 24-30.

      [2] Geng, X., Q. Wang, and Y. Xia. Facial age estimation by adaptive label distribution learning. Proceedings of the IEEE 22nd International Conference on Pattern Recognition, 2014. pp. 534-541.

      [3] Wang, X., R. Guo, and C. Kambhamettu. Deeply-learned feature for age estimation. Proceedings of the IEEE Winter Conference on Applications of Computer Vision, 2015. pp. 534-541.

      [4] qtait, M., F. Mohamad, and M. Mamat. Feature extraction for face recognition via Active Shape Model (ASM) and Active Appearance Model (AAM). IOP Conference Series: Materials Science and Engineering. 2018. 332(1): 1-9.

      [5] Dibeklioğlu, H., Alnajar, F., Salah, A. A., & Gevers, T. Combining facial dynamics with appearance for age estimation. IEEE Transactions on Image Processing, 2015. 24(6): 1928-1943.

      [6] Sai, P.-K., J.-G. Wang, and E.-K. Teoh, Facial age range estimation with extreme learning machines. Neurocomputing, 2015. 149: 364-372.

      [7] Niu, Z., Zhou, M., Wang, L., Gao, X., & Hua, G. Ordinal regression with multiple output CNN for age estimation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2016. pp. 4920-4928.

      [8] Ricanek, K. and T. Tesafaye. Morph: A longitudinal image database of normal adult age-progression. Proceedings of the IEEE 7th International Conference on Automatic Face and Gesture Recognition, 2006. pp. 341-345.

      [9] Cootes, T.F., G.J. Edwards, and C.J. Taylor, Active appearance models. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2001. 23(6): p. 681-685.

      [10] Cover, T. and P. Hart, Nearest neighbor pattern classification. IEEE Transactions on Information Theory, 1967. 13(1): 21-27.

      [11] Burges, C.J., A tutorial on support vector machines for pattern recognition. Data Mining and Knowledge Discovery, 1998. 2(2): 121-167.

      [12] Yan, Y., Ricci, E., Subramanian, R., Liu, G., & Sebe, N. Multitask linear discriminant analysis for view invariant action recognition. IEEE Transactions on Image Processing, 2014. 23(12): 5599-5611.

      [13] Hotelling, H., Relations between two sets of variates. Biometrika, 1936. 28(3/4): 321-377.

      [14] Chen, X., Yang, J., Ye, Q., & Liang, J. Recursive projection twin support vector machine via within-class variance minimization. Pattern Recognition, 2011. 44(10-11): 2643-2655.




Article ID: 24681
DOI: 10.14419/ijet.v7i3.28.24681

Copyright © 2012-2015 Science Publishing Corporation Inc. All rights reserved.