Login / Signup

A New DCT-FFT Fusion Based Method for Caption and Scene Text Classification in Action Video Images.

Lokesh NandanwarPalaiahnakote ShivakumaraSuvojit MannaUmapada PalTong LuMichael Blumenstein
Published in: ICPRAI (2020)
Keyphrases
  • video images
  • text classification
  • object recognition
  • image compression
  • image processing
  • three dimensional
  • video sequences
  • d objects
  • low cost
  • high speed
  • d scene