Weak Supervision for Generating Pixel-Level Annotations in Scene Text Segmentation.

Simone Bonechi Paolo Andreini Monica Bianchini Franco Scarselli

Published in: CoRR (2019)

Keyphrases

pixel level
text segmentation
superpixels
image fusion
multiple images
d scene
foreground objects
video sequences
dynamic scenes
three dimensional
complex scenes
image sequences
single image
input image
image regions
image features
multiscale
natural images
image retrieval
information retrieval