Feature extraction of video using artificial neural network

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

Research output: Contribution to journalArticlepeer-review

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
Pages (from-to)25-40
Number of pages16
JournalInternational Journal of Cognitive Informatics and Natural Intelligence
Volume11
Issue number2
DOIs
Publication statusPublished - 2017 Apr 1
Externally publishedYes

Keywords

  • Artificial neural network
  • Deep neural network
  • Feature extraction
  • Form analysis
  • Identity mapping
  • State trajectory
  • Table tennis

ASJC Scopus subject areas

  • Software
  • Human-Computer Interaction
  • Artificial Intelligence

Fingerprint Dive into the research topics of 'Feature extraction of video using artificial neural network'. Together they form a unique fingerprint.

Cite this