Feature extraction of video

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

Research output: Chapter in Book/Report/Conference proceedingConference contribution

4 Citations (Scopus)

Abstract

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.

Original languageEnglish
Title of host publicationProceedings of 2016 IEEE 15th International Conference on Cognitive Informatics and Cognitive Computing, ICCI*CC 2016
EditorsKostas Plataniotis, Bernard Widrow, Newton Howard, Lotfi A. Zadeh, Yingxu Wang
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages465-470
Number of pages6
ISBN (Electronic)9781509038466
DOIs
Publication statusPublished - 2017 Feb 21
Externally publishedYes
Event15th IEEE International Conference on Cognitive Informatics and Cognitive Computing, ICCI*CC 2016 - Stanford, United States
Duration: 2016 Aug 222016 Aug 23

Publication series

NameProceedings 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
Country/TerritoryUnited States
CityStanford
Period16/8/2216/8/23

Keywords

  • Deep neural network
  • Feature extritetion
  • Identity mapping
  • State trajectory

ASJC Scopus subject areas

  • Cognitive Neuroscience
  • Artificial Intelligence
  • Software
  • Computer Vision and Pattern Recognition
  • Information Systems

Fingerprint

Dive into the research topics of 'Feature extraction of video'. Together they form a unique fingerprint.

Cite this