| Authors |
|
| Publication date |
2013
|
| Book title |
MM '13
|
| Book subtitle |
proceedings of the 2013 ACM Multimedia Conference : October 21-25, 2013, Barcelona, Spain
|
| ISBN |
|
| Event |
2013 ACM Multimedia Conference
|
| Volume | Issue number |
2
|
| Pages (from-to) |
757-760
|
| Publisher |
New York: ACM
|
| Organisations |
-
Faculty of Science (FNWI) - Informatics Institute (IVI)
|
| Abstract |
This paper focuses on fine-grained classification by detecting photographed text in images. We introduce a text detection method that does not try to detect all possible foreground text regions but instead aims to reconstruct the scene background to eliminate non-text regions. Object cues such as color, contrast, and objectiveness are used in corporation with a random forest classifier to detect background pixels in the scene. Results on two publicly available datasets ICDAR03 and a fine-grained Building subcategories of ImageNet shows the effectiveness of the proposed method.
|
| Document type |
Conference contribution
|
| Language |
English
|
| Published at |
https://doi.org/10.1145/2502081.2502197
|
| Other links |
http://www.science.uva.nl/research/publications/2013/KaraogluICM2013
|
|
Permalink to this page
|