본문 바로가기
  • Home

Similar Movie Retrieval using Low Peak Feature and Image Color

  • Journal of The Korea Society of Computer and Information
  • Abbr : JKSCI
  • 2009, 14(8), pp.51-58
  • Publisher : The Korean Society Of Computer And Information
  • Research Area : Engineering > Computer Science

정명범 1 Il Ju, Ko 1

1숭실대학교

Accredited

ABSTRACT

In this paper, we propose search algorithm using Low Peak Feature of audio and image color value by which similar movies can be identified. Combing through entire video files for the purpose of recognizing and retrieving matching movies requires much time and memory space. Moreover, these methods still share a critical problem of erroneously recognizing as being different matching videos that have been altered only in resolution or converted merely with a different codec. Thus we present here a similar-video-retrieval method that relies on analysis of audio patterns, whose peak features are not greatly affected by changes in the resolution or codec used and image color values, which are used for similarity comparison. The method showed a 97.7% search success rate, given a set of 2,000 video files whose audio-bit-rate had been altered or were purposefully written in a different codec.

Citation status

* References for papers published after 2023 are currently being built.