A pyramidal neural network for visual pattern recognition
A pyramidal neural network for visual pattern recognition
复制标题
DOI：
10.1109/tnn.2006.884677
复制
发表时间：
2007-03-01
影响因子：
--
通讯作者：
Bouzerdoum, Abdesselam
中科院分区：
文献类型：
--
作者：
Phung, Son Lam;Bouzerdoum, Abdesselam
在本文中，我们提出了一个新的神经结构的视觉模式分类的动机。图像金字塔和局部感受野的两个概念。这种新的架构称为金字塔神经网络（Pyramidal neural network，PyraNet），具有两种处理层的层次结构：金字塔层和一维（1-D）层。在新网络中，训练非线性二维（2-D）神经元来执行图像特征提取和降维。我们提出并分析了PyraNct的五种训练方法[梯度下降（GD），动量梯度下降，弹性反向传播（RPROP），Polak-Ribiere共轭梯度（CG）和Levenberg-Marquirt（LM）]以及两种误差函数[均方误差（mse）和交叉熵（CE）]。在本文中，我们应用PyraNet从面部图像中确定性别，并将其在标准面部识别技术（FERET）数据库上的性能与三种分类器进行比较：卷积神经网络（NN），k-最近邻（k-NN）和支持向量机（SVNI）。
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 PyraNct [gradient descent (GD), gradient descent with momentum, resilient back-propagation (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 (SVNI).