HIERARCHICAL STRUCTURE BASED CONVOLUTIONAL NEURAL NETWORK FOR FACE RECOGNITION
- 24 September 2013
- journal article
- research article
- Published by World Scientific Pub Co Pte Ltd in International Journal of Computational Intelligence and Applications
- Vol. 12 (03)
Abstract
In this paper, a hierarchical structure based convolutional neural network is proposed to provide the ability for robust information processing. The weight sharing ability of convolutional neural networks (CNNs) is considered as a level of hierarchy in these networks. Weight sharing reduces the number of free parameters and improves the generalization ability. In the proposed structure, a small CNN which is used for feature extractor is shared between the whole input image pixels. A scalable architecture for implementing extensive CNNs is resulted using a smaller and modularized trainable network to solve a large and complicated task. The proposed structure causes less training time, fewer numbers of parameters and higher test data accuracy. The recognition accuracy for recognizing unseen data shows improvement in generalization. Also presented are application examples for face recognition. The comprehensive experiments completed on ORL, Yale and JAFFE face databases show improved classification rates and reduced training time and network parameters.Keywords
This publication has 8 references indexed in Scilit:
- Design of face recognition algorithm using PCA -LDA combined for hybrid data pre-processing and polynomial-based RBF neural networks : Design and its applicationExpert Systems with Applications, 2013
- Efficient linear discriminant analysis with locality preserving for face recognitionPattern Recognition, 2012
- FUZZY MEASURE BASED ADAPTIVE METHODS FOR ILLUMINATION INVARIANT FACE RECOGNITIONInternational Journal of Computational Intelligence and Applications, 2011
- Selection and fusion of facial features for face recognitionExpert Systems with Applications, 2008
- FACE RECOGNITION IN COLOUR IMAGES USING NEURAL NETWORKS AND GENETIC ALGORITHMSInternational Journal of Computational Intelligence and Applications, 2005
- A multiple circular path convolution neural network system for detection of mammographic massesIEEE Transactions on Medical Imaging, 2002
- Gradient-based learning applied to document recognitionProceedings of the IEEE, 1998
- Face recognition: a convolutional neural-network approachIEEE Transactions on Neural Networks, 1997