2004
@article{JKJ2004,
vgclass = {refpap},
author = {Keechul Jung and Kwang In Kim and Anil K. Jain},
title = {Text information extraction in images and video: a
survey},
journal = {Pattern Recognition},
volume = {37},
number = {5},
pages = {977--997},
month = {May},
year = {2004},
url = {http://dx.doi.org/10.1016/j.patcog.2003.10.012},
abstract = {Text data present in images and video contain useful
information for automatic annotation, indexing, and structuring of
images. Extraction of this information involves detection,
localization, tracking, extraction, enhancement, and recognition of the
text from a given image. However, variations of text due to differences
in size, style, orientation, and alignment, as well as low image
contrast and complex background make the problem of automatic text
extraction extremely challenging. While comprehensive surveys of
related problems such as face detection, document analysis, and image \&
video indexing can be found, the problem of text information extraction
is not well surveyed. A large number of techniques have been proposed
to address this problem, and the purpose of this paper is to classify
and review these algorithms, discuss benchmark data and performance
evaluation, and to point out promising directions for future
research.},
}