Multi-Column Deep Neural Networks for Offline Handwritten Chinese Character Classification
arXiv:1309.0261
Abstract
Our Multi-Column Deep Neural Networks achieve best known recognition rates on Chinese characters from the ICDAR 2011 and 2013 offline handwriting competitions, approaching human performance.
5 pages, 1 figure, IDSIA tech report
Cited by in corpus (6)
- Deep Learning in Neural Networks: An Overview
- Handwritten Isolated Bangla Compound Character Recognition: a new benchmark using a novel deep learning approach
- Location Sensitive Deep Convolutional Neural Networks for Segmentation of White Matter Hyperintensities
- Online and Offline Handwritten Chinese Character Recognition: A Comprehensive Study and New Benchmark
- DenseRAN for Offline Handwritten Chinese Character Recognition
- My First Deep Learning System of 1991 + Deep Learning Timeline 1962-2013