Multi-Column Deep Neural Networks for offline handwritten Chinese character classification

Multi-Column Deep Neural Networks achieve state of the art recognition rates on Chinese characters from the ICDAR 2011 and 2013 offline handwriting competitions, approaching human accuracy. This performance is the result of averaging 11-layers deep networks with hundreds of maps per layer, trained o...

Full description

Saved in:
Bibliographic Details
Published in:2015 International Joint Conference on Neural Networks (IJCNN) 2015-07, p.1-6
Main Authors: Ciresan, Dan, Meier, Ueli
Format: Article
Language:English
Subjects:
Character recognition
Classification
Conferences
Distortion
Graphics processing units
Handwriting recognition
Human
Kernel
Neural networks
Citations: Items that cite this one
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Multi-Column Deep Neural Networks achieve state of the art recognition rates on Chinese characters from the ICDAR 2011 and 2013 offline handwriting competitions, approaching human accuracy. This performance is the result of averaging 11-layers deep networks with hundreds of maps per layer, trained on raw, distorted images to prevent them from overfitting. The entire framework runs on a normal desktop computer with a CUDA capable graphics card.
ISSN:2161-4393
2161-4407
DOI:10.1109/IJCNN.2015.7280516