Difference between revisions of "Publications/huynh.16.icpr"
From LRDE
Duy Huýnh Lê (talk | contribs) |
|||
| (8 intermediate revisions by 2 users not shown) | |||
| Line 6: | Line 6: | ||
| booktitle = Proceedings of the 23st International Conference on Pattern Recognition (ICPR) |
| booktitle = Proceedings of the 23st International Conference on Pattern Recognition (ICPR) |
||
| address = Cancún, México |
| address = Cancún, México |
||
| + | | pages = 4029 to 4034 |
||
| − | | optpages = 485--488 |
||
| publisher = IEEE Computer Society |
| publisher = IEEE Computer Society |
||
| − | | lrdeprojects = |
+ | | lrdeprojects = Olena |
| − | | abstract = Many text segmentation methods are elaborate and thus are not suitable to real-time implementation on mobile devices. |
+ | | abstract = Many text segmentation methods are elaborate and thus are not suitable to real-time implementation on mobile devices. Having an efficient and effective method, robust to noiseblur, or uneven illumination, is interesting due to the increasing number of mobile applications needing text extraction. We propose a hierarchical image representationbased on the morphological Laplace operator, which is used to give a robust text segmentation. This representation relies on several very sound theoretical tools; its computation eventually translates to a simple labeling algorithm, and for text segmentation and grouping, to an easy tree-based processing. We also show that this method can also be applied to document binarization, with the interesting feature of getting also reverse-video text. |
| − | | note = To appear |
||
| lrdepaper = http://www.lrde.epita.fr/dload/papers/huynh.16.icpr.pdf |
| lrdepaper = http://www.lrde.epita.fr/dload/papers/huynh.16.icpr.pdf |
||
| lrdekeywords = Image |
| lrdekeywords = Image |
||
| Line 16: | Line 15: | ||
| type = inproceedings |
| type = inproceedings |
||
| id = huynh.16.icpr |
| id = huynh.16.icpr |
||
| + | | identifier = doi:10.1109/ICPR.2016.7900264 |
||
| bibtex = |
| bibtex = |
||
@InProceedings<nowiki>{</nowiki> huynh.16.icpr, |
@InProceedings<nowiki>{</nowiki> huynh.16.icpr, |
||
| Line 26: | Line 26: | ||
address = <nowiki>{</nowiki>Canc\'un, M\'exico<nowiki>}</nowiki>, |
address = <nowiki>{</nowiki>Canc\'un, M\'exico<nowiki>}</nowiki>, |
||
month = dec, |
month = dec, |
||
| − | + | pages = <nowiki>{</nowiki>4029--4034<nowiki>}</nowiki>, |
|
publisher = <nowiki>{</nowiki>IEEE Computer Society<nowiki>}</nowiki>, |
publisher = <nowiki>{</nowiki>IEEE Computer Society<nowiki>}</nowiki>, |
||
abstract = <nowiki>{</nowiki> Many text segmentation methods are elaborate and thus are |
abstract = <nowiki>{</nowiki> Many text segmentation methods are elaborate and thus are |
||
| Line 42: | Line 42: | ||
can also be applied to document binarization, with the |
can also be applied to document binarization, with the |
||
interesting feature of getting also reverse-video text.<nowiki>}</nowiki>, |
interesting feature of getting also reverse-video text.<nowiki>}</nowiki>, |
||
| − | + | doi = <nowiki>{</nowiki>10.1109/ICPR.2016.7900264<nowiki>}</nowiki> |
|
<nowiki>}</nowiki> |
<nowiki>}</nowiki> |
||
Latest revision as of 17:01, 27 May 2021
- Authors
- Lê Duy Huỳnh, Yongchao Xu, Thierry Géraud
- Where
- Proceedings of the 23st International Conference on Pattern Recognition (ICPR)
- Place
- Cancún, México
- Type
- inproceedings
- Publisher
- IEEE Computer Society
- Projects
- Olena
- Keywords
- Image
- Date
- 2016-07-13
Abstract
Many text segmentation methods are elaborate and thus are not suitable to real-time implementation on mobile devices. Having an efficient and effective method, robust to noiseblur, or uneven illumination, is interesting due to the increasing number of mobile applications needing text extraction. We propose a hierarchical image representationbased on the morphological Laplace operator, which is used to give a robust text segmentation. This representation relies on several very sound theoretical tools; its computation eventually translates to a simple labeling algorithm, and for text segmentation and grouping, to an easy tree-based processing. We also show that this method can also be applied to document binarization, with the interesting feature of getting also reverse-video text.
Documents
Bibtex (lrde.bib)
@InProceedings{ huynh.16.icpr,
author = {L\^e Duy {Hu\`ynh} and Yongchao Xu and Thierry G\'eraud},
title = {Morphology-Based Hierarchical Representation with
Application to Text Segmentation in Natural Images},
booktitle = {Proceedings of the 23st International Conference on
Pattern Recognition (ICPR)},
year = 2016,
address = {Canc\'un, M\'exico},
month = dec,
pages = {4029--4034},
publisher = {IEEE Computer Society},
abstract = { Many text segmentation methods are elaborate and thus are
not suitable to real-time implementation on mobile devices.
Having an efficient and effective method, robust to noise,
blur, or uneven illumination, is interesting due to the
increasing number of mobile applications needing text
extraction. We propose a hierarchical image representation,
based on the morphological Laplace operator, which is used
to give a robust text segmentation. This representation
relies on several very sound theoretical tools; its
computation eventually translates to a simple labeling
algorithm, and for text segmentation and grouping, to an
easy tree-based processing. We also show that this method
can also be applied to document binarization, with the
interesting feature of getting also reverse-video text.},
doi = {10.1109/ICPR.2016.7900264}
}