Abstract
In this paper we first present an effective image description method for facial expression recognition, which is a variation of local directional pattern (LDP). Then we introduce weightings on the modular’s LDP and investigate the effect on recognition rates with different weightings. Finally, the overlapped block is proposed when using LDP and proposed method. For recognition, this paper adopts PCA+LDP subspace method for feature reduction, and the nearest neighbor classifier is used in classification. The results of extensive experiments on benchmark datasets JAFFE and Cohn-Kanade illustrate that the proposed method not only can obtain better recognition rate but also have speed advantage. Moreover, the appropriately selected weightings and regional overlapping can improve recognition rates for both proposed method and LDP method.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Niu, Z., Qiu, X.: Facial expression recognition based on weighted principal component analysis and support vector machines. In: Int. Conf. on Advanced Computer Theory and Engineering. IEEE (2010)
Gritti, T., Shan, C., Jeanne, V., Braspenning, R.: Local Features based Facial Expression Recognition with Face Registration Errors 978-1-4244-1/08/2008. IEEE
Murthy, G.R.S., Jadon, R.S.: Effectiveness of Eigenspaces for Facial Expressions Recognition. International Journal of Computer Theory and Engineering 1(5) (December 2009)
Fasel, B., Luttin, J.: Automatic Facial Expression Analysis: a survey. Pattern Recognition 36(1), 259–275 (2003)
Zhang, Z., et al.: Comparition between Geometry-Based and Gobor-wavelet-based Facial Expression Recognition Using Multi-layer Perception. In: Proc. IEEE Int. Conf. Auto. Face Gesture Recog., pp. 454–459 (April 1998)
Praseeda Lekshmi, V., Sasikumar, M.: Analysis of Facial Expression using Gabor and SVM. International Journal of Recent Trends in Engineering 1(2) (May 2009)
Xue, W.: Facial Expression Recognition Based on GaborFilter and SVM. Chinese Journal of Electronics 15(4A) (2006)
Shan, C., Gong, S., McOwan, P.W.: Facial expression recognition based on Local Binary Patterns:A comprehensive study. Image and Vision Computing 27, 803–816 (2009)
Kabir, M.H., Jabid, T., Chae, O.: A Local Directional Pattern Variance (LDPv) based Face Descriptor for Human Facial Expression Recognition. IEEE (2010), doi:10.1109/AVSS.2010. 9978 -0-7695-4264-5/10 © 2010 IEEE
Ojala, T., Pietikainen, M.: Multiresolution Gray-Scale and Rotation with Local Binary Patterns and Linear Programming. IEEE Trans.Pattern Anal. Mach.Intell. 29(6), 915–928 (2007)
Jabid, T., Kabir, M.H., Chae, O.S.: Local Directional Pattern (LDP) for Face Recognition. In: IEEE Int. Conf. Consum. Electron. 2010, pp. 329–330 (2010)
Jabid, T., Kabir, M.H., Chae, O.S.: Local Directional Pattern(LDP)-A robust Descriptor for Object Recognition. In: IEEE Int. Conf. on AVSS (2010) 978-0-7695-4264-5/10
Jabid, T., Kabir, M.H., Chae, O.S.: Gender Classification using Directional Pattern(LDP). IEEE Pattern Recognition (2010)
Jabid, T., Kabir, M.H., Chae, O.S.: Robust Facial Expression Recognition Based on Local Directional Pattern. ETRI Jounal 32(5) (October 2010)
Jaffe dataset, http://www.kasrl.org/jaffe.html
Kanade, T., Cohn, J., Tian, Y.: Comprehensive Database for Facial Expression Analysis. In: Proc. IEEE Int’l. Conf. Face and Gesture Recognition (AFGR 2000), pp. 46–53 (2000)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2011 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Xu, T., Zhou, J., Wang, Y. (2011). A Variation of Local Directional Pattern and Its Application for Facial Expression Recognition. In: Kim, Th., Adeli, H., Ramos, C., Kang, BH. (eds) Signal Processing, Image Processing and Pattern Recognition. SIP 2011. Communications in Computer and Information Science, vol 260. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-27183-0_5
Download citation
DOI: https://doi.org/10.1007/978-3-642-27183-0_5
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-27182-3
Online ISBN: 978-3-642-27183-0
eBook Packages: Computer ScienceComputer Science (R0)