Facial expression recognition base on weighted KNN and RF. (English) Zbl 1400.68189
Cocchiarella, Luigi (ed.), ICGG 2018 – Proceedings of the 18th international conference on geometry and graphics. 40th anniversary – Milan, Italy, August 3–7, 2018. In 2 volumes. Cham: Springer; Milan: Politecnico de Milano (ISBN 978-3-319-95587-2/pbk; 978-3-319-95588-9/ebook). Advances in Intelligent Systems and Computing 809, 1315-1323 (2019).
Summary: To solve the problem of the large computation and low recognition rate which caused by the K-Nearest Neighbor (KNN) algorithm, a new approach for facial expression recognition based on weighted K-Nearest Neighbor and Random Forest (RF) is presented in this paper. First of all, the features of the static facial expression image are extracted by the Supervised Descent Method (SDM), then calculate the average distance between samples and use it to divide test samples, select different classifier for different test samples base on the characteristic of weighted KNN and RF. Finally, the result of experiment on JAFFE database show that the proposed algorithm can not only achieve better recognition rate, but also simplify the computation complexity.
For the entire collection see [Zbl 1403.00028].
For the entire collection see [Zbl 1403.00028].
MSC:
| 68T10 | Pattern recognition, speech recognition |
| 68U10 | Computing methodologies for image processing |
References:
| [1] | Owusu, E., Zhan, Y.Z., Mao, Q.R.: An SVM-AdaBoost facial expression recognition system. Appl. Intell. 40(3), 536-545 (2014) · doi:10.1007/s10489-013-0478-9 |
| [2] | Liu, Z.H., Wang, H.Z, Yan, Y. et al.: Effective facial expression recognition via the boosted convolutional neural network. In: Chinese Conference on Computer Vision(CCCV), Xi an, China, pp. 179-188 (2015) |
| [3] | Zhou, S.Z., Feng, G., Xie, J.F.: Facial expression recognition based on classification tree. In: Chinese conference on biometric recognition, Shenyang, China, pp. 128-135 (2014) |
| [4] | Zhi, R.C., Ruan, Q.Q., Wang, Z.F.: Facial expression recognition via sparse representation. IEICE Trans. 95, 2347-2350 (2012) · doi:10.1587/transinf.E95.D.2347 |
| [5] | Wang, Q.T., Jia, K.B., Liu, P.Y.: Design and implementation of remote facial expression recognition surveillance system based on PCA and KNN algorithms. In: International conference on intelligent information hiding and multimedia signal processing, Adelaide, SA, Australia, pp. 314-317 (2015) |
| [6] | Wang, X.H., Huang, Y.Z., Zhang, S.Q.: Face expression recognition combined with FSVM and KNN. Microelectron. Comput. 30(10), 38-41 |
| [7] | Zineb, E., Othmane, E.M., et al.: Robust facial expression recognition system based on hidden Markov models. Int. J. Multimedia Inform. Retrieval 5, 229-236 (2016) · doi:10.1007/s13735-016-0113-8 |
| [8] | Breiman, L.: Random forests. Mach. Learn. 45(1), 5-32 (2001) · Zbl 1007.68152 · doi:10.1023/A:1010933404324 |
| [9] | Xiong, X.H., Fdl, T.: Supervised descent method and its applications to face alignment. In: Conference on computer vision and pattern recognition (CVPR), Portland, Oregon, pp. 532-539 (2013) |
| [10] | Ghosh, A.K.: On optimum choice of k in nearest neighbor classification. Comput. Stat. Data Anal. 50(11), 3113-3123 (2006) · Zbl 1445.62144 · doi:10.1016/j.csda.2005.06.007 |
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.
