Difference between revisions of "Publications/fabrizio.16.ijdar"
From LRDE
Line 3: | Line 3: | ||
| date = 2016-04-08 |
| date = 2016-04-08 |
||
| authors = Jonathan Fabrizio, Myriam Robert-Seidowsky, Séverine Dubuisson, Stefania Calarasanu, Raphaël Boissel |
| authors = Jonathan Fabrizio, Myriam Robert-Seidowsky, Séverine Dubuisson, Stefania Calarasanu, Raphaël Boissel |
||
− | | title = TextCatcher: |
+ | | title = TextCatcher: A method to detect curved and challenging text in natural scenes |
| journal = International Journal on Document Analysis and Recognition |
| journal = International Journal on Document Analysis and Recognition |
||
| volume = 19 |
| volume = 19 |
||
Line 16: | Line 16: | ||
| type = article |
| type = article |
||
| id = fabrizio.16.ijdar |
| id = fabrizio.16.ijdar |
||
+ | | identifier = doi:10.1007/s10032-016-0264-4 |
||
| bibtex = |
| bibtex = |
||
@Article<nowiki>{</nowiki> fabrizio.16.ijdar, |
@Article<nowiki>{</nowiki> fabrizio.16.ijdar, |
||
Line 21: | Line 22: | ||
S\'everine Dubuisson and Stefania Calarasanu and Rapha\"el |
S\'everine Dubuisson and Stefania Calarasanu and Rapha\"el |
||
Boissel<nowiki>}</nowiki>, |
Boissel<nowiki>}</nowiki>, |
||
− | title = <nowiki>{</nowiki>TextCatcher: |
+ | title = <nowiki>{</nowiki>TextCatcher: <nowiki>{</nowiki>A<nowiki>}</nowiki> method to detect curved and challenging |
text in natural scenes<nowiki>}</nowiki>, |
text in natural scenes<nowiki>}</nowiki>, |
||
journal = <nowiki>{</nowiki>International Journal on Document Analysis and |
journal = <nowiki>{</nowiki>International Journal on Document Analysis and |
||
Line 47: | Line 48: | ||
competition, and the third one contains photographs we have |
competition, and the third one contains photographs we have |
||
taken with various daily life texts. We present both |
taken with various daily life texts. We present both |
||
− | qualitative and quantitative results.<nowiki>}</nowiki> |
+ | qualitative and quantitative results.<nowiki>}</nowiki>, |
+ | doi = <nowiki>{</nowiki>10.1007/s10032-016-0264-4<nowiki>}</nowiki> |
||
<nowiki>}</nowiki> |
<nowiki>}</nowiki> |
||
Latest revision as of 17:00, 27 May 2021
- Authors
- Jonathan Fabrizio, Myriam Robert-Seidowsky, Séverine Dubuisson, Stefania Calarasanu, Raphaël Boissel
- Journal
- International Journal on Document Analysis and Recognition
- Type
- article
- Publisher
- Springer
- Projects
- Olena
- Keywords
- Image
- Date
- 2016-04-08
Abstract
In this paper, we propose a text detection algorithm which is hybrid and multi-scale. First, it relies on a connected component-based approach: After the segmentation of the image, a classification step using a new wavelet descriptor spots the letters. A new graph modeling and its traversal procedure allow to form candidate text areas. Second, a texture-based approach discards the false positives. Finally, the detected text areas are precisely cut out and a new binarization step is introduced. The main advantage of our method is that few assumptions are put forward. Thus, “challenging texts” like multi-sizedmulti-colored, multi-oriented or curved text can be localized. The efficiency of TextCatcher has been validated on three different datasets: Two come from the ICDAR competition, and the third one contains photographs we have taken with various daily life texts. We present both qualitative and quantitative results.
Documents
Bibtex (lrde.bib)
@Article{ fabrizio.16.ijdar, author = {Jonathan Fabrizio and Myriam Robert-Seidowsky and S\'everine Dubuisson and Stefania Calarasanu and Rapha\"el Boissel}, title = {TextCatcher: {A} method to detect curved and challenging text in natural scenes}, journal = {International Journal on Document Analysis and Recognition}, year = 2016, volume = 19, number = 2, publisher = {Springer}, pages = {99--117}, month = feb, abstract = {In this paper, we propose a text detection algorithm which is hybrid and multi-scale. First, it relies on a connected component-based approach: After the segmentation of the image, a classification step using a new wavelet descriptor spots the letters. A new graph modeling and its traversal procedure allow to form candidate text areas. Second, a texture-based approach discards the false positives. Finally, the detected text areas are precisely cut out and a new binarization step is introduced. The main advantage of our method is that few assumptions are put forward. Thus, ``challenging texts'' like multi-sized, multi-colored, multi-oriented or curved text can be localized. The efficiency of TextCatcher has been validated on three different datasets: Two come from the ICDAR competition, and the third one contains photographs we have taken with various daily life texts. We present both qualitative and quantitative results.}, doi = {10.1007/s10032-016-0264-4} }