A Pyramidal Neural Network For Visual Pattern Recognition
- 5 March 2007
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks
- Vol. 18 (2) , 329-343
Abstract
In this paper, we propose a new neural architecture for classification of visual patterns that is motivated by the two concepts of image pyramids and local receptive fields. The new architecture, called pyramidal neural network (PyraNet), has a hierarchical structure with two types of processing layers: Pyramidal layers and one-dimensional (1-D) layers. In the new network, nonlinear two-dimensional (2-D) neurons are trained to perform both image feature extraction and dimensionality reduction. We present and analyze five training methods for PyraNet [gradient descent (GD), gradient descent with momentum, resilient backpropagation (RPROP), Polak-Ribiere conjugate gradient (CG), and Levenberg-Marquadrt (LM)] and two choices of error functions [mean-square-error (mse) and cross-entropy (CE)]. In this paper, we apply PyraNet to determine gender from a facial image, and compare its performance on the standard facial recognition technology (FERET) database with three classifiers: The convolutional neural network (NN), the k-nearest neighbor (k-NN), and the support vector machine (SVM)Keywords
This publication has 30 references indexed in Scilit:
- Convergence of Gradient Method With Momentum for Two-Layer Feedforward Neural NetworksIEEE Transactions on Neural Networks, 2006
- Convolutional face finder: a neural architecture for fast and robust face detectionIEEE Transactions on Pattern Analysis and Machine Intelligence, 2004
- Detecting faces in images: a surveyIEEE Transactions on Pattern Analysis and Machine Intelligence, 2002
- Neural recognition in a pyramidal structureIEEE Transactions on Neural Networks, 2002
- Mixture of experts for classification of gender, ethnic origin, and pose of human facesIEEE Transactions on Neural Networks, 2000
- Neural network-based face detectionIEEE Transactions on Pattern Analysis and Machine Intelligence, 1998
- Face recognition: a convolutional neural-network approachIEEE Transactions on Neural Networks, 1997
- Human expression recognition from motion using a radial basis function network architectureIEEE Transactions on Neural Networks, 1996
- Training feedforward networks with the Marquardt algorithmIEEE Transactions on Neural Networks, 1994
- Neocognitron: A hierarchical neural network capable of visual pattern recognitionNeural Networks, 1988