Feature extraction of video

Yoshihiro Hayakawa, Takanori Oonuma, Hideyuki Kobayashi, Akiko Takahashi, Shinji Chiba, Nahomi M. Fujiki

研究成果: Conference contribution

4 被引用数 (Scopus)

抄録

In deep neural networks, which have been gaining attention in recent years, the features of input images are expressed in a middle layer. Using the information on this feature layer, high performance can be demonstrated in the image recognition field. In the present study, we achieve image recognition, without using convolutional neural networks or sparse coding, through an image feature extraction function obtained when identity mapping learning is applied to sandglass-style feed-forward neural networks. In sports form analysis, for example, a state trajectory is mapped in a low-dimensional feature space based on a consecutive series of actions. Here, we discuss ideas related to image analysis by applying the above method.

本文言語English
ホスト出版物のタイトルProceedings of 2016 IEEE 15th International Conference on Cognitive Informatics and Cognitive Computing, ICCI*CC 2016
編集者Kostas Plataniotis, Bernard Widrow, Newton Howard, Lotfi A. Zadeh, Yingxu Wang
出版社Institute of Electrical and Electronics Engineers Inc.
ページ465-470
ページ数6
ISBN(電子版)9781509038466
DOI
出版ステータスPublished - 2017 2 21
外部発表はい
イベント15th IEEE International Conference on Cognitive Informatics and Cognitive Computing, ICCI*CC 2016 - Stanford, United States
継続期間: 2016 8 222016 8 23

出版物シリーズ

名前Proceedings of 2016 IEEE 15th International Conference on Cognitive Informatics and Cognitive Computing, ICCI*CC 2016

Other

Other15th IEEE International Conference on Cognitive Informatics and Cognitive Computing, ICCI*CC 2016
国/地域United States
CityStanford
Period16/8/2216/8/23

ASJC Scopus subject areas

  • 認知神経科学
  • 人工知能
  • ソフトウェア
  • コンピュータ ビジョンおよびパターン認識
  • 情報システム

フィンガープリント

「Feature extraction of video」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