Caption Text Recognition in Video Frames by MAP Matching.

Akira Nakamura Kazuhiko Yamamoto

Published in: ICDAR (2003)

Keyphrases

video frames
map matching
caption text
text regions
video sequences
video data
object recognition
road network
automatic recognition
video images
spatio temporal
action recognition
video shots
input image
binary images
character recognition
foreground objects
three dimensional
metadata