Fast search for MPEG video clips from large video database using combined histogram features

Feifei Lee, Koji Kotani, Qiu Chen, Tadahiro Ohmi

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

Abstract

In this paper, we propose a novel fast search algorithm using combined histogram features for short MPEG video clips from large video database. There are two types of histogram features used to generate more robust features. The first one is based on the adjacent pixel intensity difference quantization (APIDQ) algorithm, which had been reliably applied to human face recognition previously. An APIDQ histogram is utilized as the feature vector of the frame image. Another one is ordinal feature which is robust to color distortion. Combined with active search [4], a temporal pruning algorithm, fast and robust video search can be realized. The proposed search algorithm has been evaluated by 6 hours of video to search for given 200 MPEG video clips which each length is 15 seconds. Experimental results show the proposed algorithm can detect the similar video clip in merely 100ms, and Equal Error Rate (ERR) of 1.5 % is achieved, which is more accurately and robust than conventional fast video search algorithm.

Original languageEnglish
Title of host publicationWCE 2010 - World Congress on Engineering 2010
Pages637-640
Number of pages4
Publication statusPublished - 2010 Dec 1
EventWorld Congress on Engineering 2010, WCE 2010 - London, United Kingdom
Duration: 2010 Jun 302010 Jul 2

Publication series

NameWCE 2010 - World Congress on Engineering 2010
Volume1

Other

OtherWorld Congress on Engineering 2010, WCE 2010
CountryUnited Kingdom
CityLondon
Period10/6/3010/7/2

Keywords

  • Adjacent pixel intensity difference quantization (APIDQ)
  • DC image
  • Fast search
  • Histogram feature
  • Video database

ASJC Scopus subject areas

  • Computer Science(all)
  • Engineering(all)

Fingerprint Dive into the research topics of 'Fast search for MPEG video clips from large video database using combined histogram features'. Together they form a unique fingerprint.

  • Cite this

    Lee, F., Kotani, K., Chen, Q., & Ohmi, T. (2010). Fast search for MPEG video clips from large video database using combined histogram features. In WCE 2010 - World Congress on Engineering 2010 (pp. 637-640). (WCE 2010 - World Congress on Engineering 2010; Vol. 1).