CNN training with graph-based sample preselection: application to handwritten character recognition

Frederic Rayar, Masanori Goto, Seiichi Uchida

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

1 被引用数 (Scopus)

抄録

In this paper, we present a study on sample preselection in large training data set for CNN-based classification. To do so, we structure the input data set in a network representation, namely the Relative Neighbourhood Graph, and then extract some vectors of interest. The proposed preselection method is evaluated in the context of handwritten character recognition, by using two data sets, up to several hundred thousands of images. It is shown that the graph-based preselection can reduce the training data set without degrading the recognition accuracy of a non pretrained CNN shallow model.

本文言語英語
ホスト出版物のタイトルProceedings - 13th IAPR International Workshop on Document Analysis Systems, DAS 2018
出版社Institute of Electrical and Electronics Engineers Inc.
ページ19-24
ページ数6
ISBN(電子版)9781538633465
DOI
出版ステータス出版済み - 6 22 2018
イベント13th IAPR International Workshop on Document Analysis Systems, DAS 2018 - Vienna, オーストリア
継続期間: 4 24 20184 27 2018

出版物シリーズ

名前Proceedings - 13th IAPR International Workshop on Document Analysis Systems, DAS 2018

その他

その他13th IAPR International Workshop on Document Analysis Systems, DAS 2018
Countryオーストリア
CityVienna
Period4/24/184/27/18

All Science Journal Classification (ASJC) codes

  • Computer Vision and Pattern Recognition
  • Signal Processing

フィンガープリント 「CNN training with graph-based sample preselection: application to handwritten character recognition」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