Conference Paper

Wavelets Based Facial Expression Recognition Using a Bank of Neural Networks

Dept. of Comput. Sci., FAST - Nat. Univ. of Comput. & Emerging Sci., Islamabad, Pakistan
DOI: 10.1109/FUTURETECH.2010.5482717 Conference: Future Information Technology (FutureTech), 2010 5th International Conference on
Source: IEEE Xplore

ABSTRACT A human face does not only identify an individual but also communicates useful information about a person's emotional state. No wonder automatic face expression recognition has become an area of immense interest within the computer science, psychology, medicine and human-computer interaction research communities. Various feature extraction techniques based on statistical to geometrical data have been used for recognition of expressions from static images as well as real time videos. In this paper we present a method for automatic recognition of facial expressions from face images by providing Discrete Wavelet Transform (DWT) features to a bank of five parallel neural networks. Each neural network is trained to recognize a particular facial expression, so that it is most sensitive to that expression. Multi-classification is achieved by combining multiple neural networks performing binary classification using oneagainst-all approach. The outputs of all neural networks are combined using a maximum function. The classification efficiency is tested on static images from the publicly available JAFFE database. The experiments using the proposed method demonstrate promising results.

Download full-text


Available from: Arfan Jaffar, Dec 24, 2013
  • [Show abstract] [Hide abstract]
    ABSTRACT: Facial expression recognition has recently become a challenging research area. Its applications include human–computer interfaces, human emotion analysis, and medical care and cure.In this paper, we present a new challenging method to recognize seven universal emotional expressions, which are happiness, neutral, angry, disgust, sadness, fear and surprise. In our approach, we identify the user׳s facial expressions from the input images, using statistical features extracted from the steerable pyramid decomposition, and classified with a Bayesian regularization neural network. The evaluation of the proposed approach in terms of recognition accuracy is achieved using two universal databases, the Japanese Female Facial Expression database and the Cohn–Kanade facial expression database. The overall accuracy rate reaches 93.33% for the first database and is about 98.13% for the second one. These results show the effectiveness of the steerable proposed algorithm.
    Engineering Applications of Artificial Intelligence 11/2014; DOI:10.1016/j.engappai.2014.11.002 · 1.96 Impact Factor
  • [Show abstract] [Hide abstract]
    ABSTRACT: In this paper, an approach for human emotion recognition system based on Undecimated Wavelet Transform (UWT) is presented. The main drawback of Discrete Wavelet Transform (DWT) is not translation invariant. Translations of an image lead to different wavelet coefficients. UWT is used to overcome this and more comprehensive feature of the decomposed image is obtained. The classification of human emotional state is achieved by extracting the energies from all sub-bands of UWT. The robust K-Nearest Neighbor (K-NN) is constructed for classification. The evaluation of the system is carried on using JApanese Female Facial Expression (JAFFE) database. Experimental results show that the proposed UWT based human emotion recognition system produces more accurate recognition rate than DWT. For 3rd level decomposition, UWT based features produces 82% classification rate while DWT based features produces 73.22%. The maximum classification rate achieved by the proposed system is 85.62% using 5th level decomposition.
    Advanced Computer Science and Information Systems (ICACSIS), 2012 International Conference on; 01/2012
  • [Show abstract] [Hide abstract]
    ABSTRACT: A method of dealing with NMF (non-negative matrix factorization) basis to enhance face recognition rate is introduced in this paper. Firstly, we use discrete wavelet transformation to produce a representation in the low frequency domain, and get basic matrix according to the NMF method. Secondly, parts of face features which possess outstanding performance are extracted by threshold value judgments, and they are used to form optimized facial subspace feature. The training and testing images are projected to the optimized subspace feature. Finally, support vector machine is used for classification. Experiments show that the improved method is workable, especially under the circumstance of partial occlusion, it achieves remarkable effects.
    Multimedia Technology (ICMT), 2011 International Conference on; 01/2011