A further step to perfect accuracy by training CNN with larger data

Seiichi Uchida, Shota Ide, Brian Kenji Iwana, Anna Zhu

研究成果: Chapter in Book/Report/Conference proceedingConference contribution

19 被引用数 (Scopus)

抄録

Convolutional Neural Networks (CNN) are on the forefront of accurate character recognition. This paper explores CNNs at their maximum capacity by implementing the use of large datasets. We show a near-perfect performance by using a dataset of about 820,000 real samples of isolated handwritten digits, much larger than the conventional MNIST database. In addition, we report a near-perfect performance on the recognition of machine-printed digits and multi-font digital born digits. Also, in order to progress toward a universal OCR, we propose methods of combining the datasets into one classifier. This paper reveals the effects of combining the datasets prior to training and the effects of transfer learning during training. The results of the proposed methods also show an almost perfect accuracy suggesting the ability of the network to generalize all forms of text.

本文言語英語
ホスト出版物のタイトルProceedings - 2016 15th International Conference on Frontiers in Handwriting Recognition, ICFHR 2016
出版社Institute of Electrical and Electronics Engineers Inc.
ページ405-410
ページ数6
ISBN(電子版)9781509009817
DOI
出版ステータス出版済み - 7 2 2016
イベント15th International Conference on Frontiers in Handwriting Recognition, ICFHR 2016 - Shenzhen, 中国
継続期間: 10 23 201610 26 2016

出版物シリーズ

名前Proceedings of International Conference on Frontiers in Handwriting Recognition, ICFHR
0
ISSN(印刷版)2167-6445
ISSN(電子版)2167-6453

その他

その他15th International Conference on Frontiers in Handwriting Recognition, ICFHR 2016
Country中国
CityShenzhen
Period10/23/1610/26/16

All Science Journal Classification (ASJC) codes

  • Computer Science Applications
  • Computer Vision and Pattern Recognition

フィンガープリント 「A further step to perfect accuracy by training CNN with larger data」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル