Classification of Handwriting Number Based on PCANet Network with Data Augmentation

DOI

10.2991/ameii-16.2016.135How to use a DOI?

Keywords

handwriting number recognition, Deep learning, PCANet Network, data augmentation

Abstract

In this paper we proposed an algorithm for classification of handwriting number which use depth of the structure of the simple convolution neural network-- PCANet Network with data augmentation. PCANet Network with data augmentation consists of four parts, one is data augmentation, two is the basic PCA filters, part three is binary quantization, four is the block-wise histograms. This simple convolution neural network improve some defects of classic convolution neural network such as training time too long, need special tuning parameters and technique problems. This allows for training networks with many features, making them insensitive to variability between class and class. Lots of experimental results show that the PCANet Network with data augmentation algorithms have higher recognition rate than the classification effect with that of SVM algorithm, BP neural network and PCANet

Copyright

© 2016, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Tianmei Guo
AU  - Jiwen Dong
AU  - Lei Wang
PY  - 2016/04
DA  - 2016/04
TI  - Classification of Handwriting Number Based on PCANet Network with Data Augmentation
BT  - Proceedings of the 2nd International Conference on Advances in Mechanical Engineering and Industrial Informatics (AMEII 2016)
PB  - Atlantis Press
SP  - 688
EP  - 693
SN  - 2352-5401
UR  - https://doi.org/10.2991/ameii-16.2016.135
DO  - 10.2991/ameii-16.2016.135
ID  - Guo2016/04
ER  -