Characterization of common videos with statistical features extracted from frame transition profiles

Abhiram Reddy Gaddampalli, Qiuming Zhu

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

Abstract

The availability of a tremendous amount of videos on Internet nowadays raises a research question of how to automatically classify and label the videos in terms of their contents so as to allow people a quick access based on a particular interest in the types and characteristics of the videos. Organizing video clips into proper categories will make the process of content-based search on large number of videos much faster and improve the accessibility. Also an ability to detect and identify the originality and the creator (author/source) according to the unique shooting characteristics of the videos will be useful in certain applications. A profile created by extracting the features of shot transitions at which the contents of video frames exhibit special patterns of changes helps categorizing videos in different types. The research of this paper experimented on three types of videos (News, Sports, and Music) to show that a content profile built on a new set of frame transition parameters and corresponding statistical measurements could be applied to reveal the specific characteristics and distinguish the different types of videos.

Original languageEnglish (US)
Title of host publication2017 IEEE Symposium Series on Computational Intelligence, SSCI 2017 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1-7
Number of pages7
ISBN (Electronic)9781538627259
DOIs
StatePublished - Feb 2 2018
Event2017 IEEE Symposium Series on Computational Intelligence, SSCI 2017 - Honolulu, United States
Duration: Nov 27 2017Dec 1 2017

Publication series

Name2017 IEEE Symposium Series on Computational Intelligence, SSCI 2017 - Proceedings
Volume2018-January

Other

Other2017 IEEE Symposium Series on Computational Intelligence, SSCI 2017
CountryUnited States
CityHonolulu
Period11/27/1712/1/17

Keywords

  • Video classification
  • content profiling
  • feature extraction
  • shot transitions
  • transitional features

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Science Applications
  • Control and Optimization

Fingerprint Dive into the research topics of 'Characterization of common videos with statistical features extracted from frame transition profiles'. Together they form a unique fingerprint.

Cite this