A trainable feature extractor for handwritten digit recognition
A trainable feature extractor for handwritten digit recognition
复制标题
DOI：
10.1016/j.patcog.2006.10.011
复制
发表时间：
2007-06-01
影响因子：
8
通讯作者：
Bloch, Gerard
中科院分区：
文献类型：
--
作者：
Lauer, Fabien;Suen, Ching Y.;Bloch, Gerard
本文主要研究手写体数字的特征提取和识别问题。介绍了一种基于LeNet5卷积神经网络架构的可训练特征提取器，以解决在没有数据先验知识的情况下黑盒方案中的第一个问题。分类任务由支持向量机执行，以增强LeNet5的泛化能力。为了提高识别率，通过仿射变换和弹性变形产生新的训练样本。在著名的MNIST数据库上进行了实验验证，结果表明，该系统的性能优于支持向量机和LeNet5，同时提供了与该数据库上最佳性能相当的性能。此外，误差进行了分析，讨论可能的增强手段及其局限性。(c)2006模式识别学会。由爱思唯尔有限公司出版。保留所有权利。
This article focuses on the problems of feature extraction and the recognition of handwritten digits. A trainable feature extractor based on the LeNet5 convolutional neural network architecture is introduced to solve the first problem in a black box scheme without prior knowledge on the data. The classification task is performed by support vector machines to enhance the generalization ability of LeNet5. In order to increase the recognition rate, new training samples are generated by affine transformations and elastic distortions. Experiments are performed on the well-known MNIST database to validate the method and the results show that the system can outperform both SVMs and LeNet5 while providing performances comparable to the best performance on this database. Moreover, an analysis of the errors is conducted to discuss possible means of enhancement and their limitations. (c) 2006 Pattern Recognition Society. Published by Elsevier Ltd. All rights reserved.