Facial expression recognition using image orientation field in limited regions and MLP neural network
- 1 May 2010
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 85-88
Abstract
In this paper, a novel approach for facial expression is introduced by using face orientation field concept. This method is not sensitive to the obstacles such as hair, eyeglasses and surrounding illumination. The computational tools of this paper have been used in previous studies for fingerprint recognition systems. However, we have adopted them for facial expression recognition. The features which extracted from orientation field are applied to the MLP neural network and this network select facial expression among six universal expressions. The presented method, have been tested on the JAFFE database and reached the average accuracy of 90.33% in recognition of facial expressions.Keywords
This publication has 8 references indexed in Scilit:
- Spatio-temporal Facial Expression Recognition Using Optical Flow and HMM2008
- Facial expression recognition based on PCA and NMF2008
- Efficient Facial Expression Recognition for Human Robot Interaction2007
- Automatic facial expression analysis: a surveyPattern Recognition, 2003
- Coding facial expressions with Gabor wavelets2002
- Efficient region tracking with parametric models of geometry and illuminationIEEE Transactions on Pattern Analysis and Machine Intelligence, 1998
- Adaptive flow orientation-based feature extraction in fingerprint imagesPattern Recognition, 1995
- Analyzing oriented patternsComputer Vision, Graphics, and Image Processing, 1987