MLP neural network using constructive training algorithm: Application to face recognition and facial expression recognition

被引：0

作者：

Boughrara H. ^{[1
]}

Chtourou M. ^{[1
]}

Amar C.B. ^{[2
]}

机构：

[1] Control and Energy Management Laboratory, University of Sfax, ENIS, Sfax, BP.1173

[2] REGIM-Lab.: Research Groups in Intelligent Machines, University of Sfax, ENIS, Sfax, BP.1173

来源：

Boughrara, Hayet (hayet.boughrara@laposte.net) | 1600年 / Inderscience Enterprises Ltd., 29, route de Pre-Bois, Case Postale 856, CH-1215 Geneva 15, CH-1215, Switzerland卷 / 16期

关键词：

constructive training algorithm; MLP; multi layer perceptron; back-propagation; face recognition; facial expression recognition; PFI; perceived facial images; Gabor filters;

D O I：

10.1504/IJISTA.2017.081316

中图分类号：

学科分类号：

摘要：

This paper presents a constructive training algorithm applied to face recognition and facial expression recognition. The multi layer perceptron (MLP) neural network is formed by a single hidden layer using a predefined number of neurons and a small number of training patterns. During the learning, the hidden neuron number is incremented when the mean square error (MSE) on the training data (TD) is not reaches a predefined value. Input patterns are learned incrementally until all patterns of TD are presented. The proposed algorithm allows to find synthesis parameters as the number of patterns corresponding for subsets of each class to be presented initially in the training step, the initial number of hidden neurons, the iterations number as well as the MSE value. The feature extraction stage is based on the perceived facial images and the Gabor filter. Compared to the literature review and the fixed MLP architecture, experimental results demonstrate the efficiency of the proposed approach. Copyright © 2017 Inderscience Enterprises Ltd.

引用

页码：53 / 79

页数：26

共 70 条

[1]

Abid S., Chtourou M., Djemel M., Pseudo-entropy based pruning algorithm for feed forward neural networks, Australian Journal of Basic and Applied Sciences, 7, 8, pp. 214-223, (2013)

[2]

Banziger T., Scherer K.R., Introducing the geneva multimodal emotion portrayal (gemep) corpus, Blueprint for Affective Computing: A Sourcebook, pp. 271-294, (2010)

[3]

Bejani M., Gharavian D., Charkari N.M., Audiovisual emotion recognition using ANOVA feature selection method and multi-classifier neural networks, Neural Computing and Applications, 24, 2, pp. 399-412, (2014)

[4]

Ben Aoun N., Mejdoub M., Ben Amar C., Graph-based approach for human action recognition using spatio-temporal features, Journal of Visual Communication and Image Representation, 25, 2, pp. 329-338, (2014)

[5]

Borgi M.A., Labate D., El'Arbi M., Ben Amar C., Regularized shearlet network for face recognition using single sample per person, ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings, pp. 514-518, (2014)

[6]

Bouchrika T., Zaied M., Jemai O., Ben Amar C., Neural solutions to interact with computers by hand gesture recognition, Multimedia Tools and Applications, 72, 3, pp. 2949-2975, (2013)

[7]

Boughrara H., Chen L., Ben Amar C., Chtourou M., Face recognition under varying facial expression based on perceived facial images and local feature matching, International Conference on Information Technology and E-Service, pp. 1-6, (2012)

[8]

Boughrara H., Chtourou M., Ben Amar C., MLP neural network based face recognition system using constructive training algorithm, International Conference on Multimedia Computing and System, pp. 233-238, (2012)

[9]

Boughrara H., Chen L., Ben Amar C., Chtourou M., Facial expression recognition based on perceived facial images and local feature matching, International Conference on Image Analysis and Processing, pp. 591-600, (2013)

[10]

Boughrara H., Chtourou M., Ben Amar C., Chen L., Face recognition based on perceived facial images and MLP neural network using constructive training algorithm, Journal of the IET Computer Vision, 8, 6, pp. 729-739, (2014)

← 1 2 3 4 5 6 7 →