| Presentation | 2013-03-15 Automatic Word Ground Truth Generation for Camera Captured Documents Sheraz AHMED, Koichi KISE, Masakazu IWAMURA, Marcus LIWICKI, Andreas DENGEL, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | A database for camera captured documents is useful to train OCRs to obtain better performance. However, no dataset exists for camera captured documents because it is very laborious and costly to build these datasets manually. In this paper, a fully automatic approach allowing building the very large scale (i. e., millions of images) labeled camera captured documents dataset is proposed. The proposed approach does not require any human intervention in labeling. Evaluation of samples generated by the proposed approach shows that more than 97% of the images are correctly labeled. Novelty of the proposed approach lies in the use of document image retrieval for automatic labeling, especially for camera captured documents, which contain different distortions specific to camera, e.g., blur, perspective distortion, etc. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Ground truth / Locally Likely Arrangement Hashing (LLAH) / Camera Captured Documents / Perspective distortion / Blur |
| Paper # | PRMU2012-204 |
| Date of Issue |
| Conference Information | |
| Committee | PRMU |
|---|---|
| Conference Date | 2013/3/7(1days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | |
| Chair | |
| Vice Chair | |
| Secretary | |
| Assistant | |
| Paper Information | |
| Registration To | Pattern Recognition and Media Understanding (PRMU) |
|---|---|
| Language | ENG |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Automatic Word Ground Truth Generation for Camera Captured Documents |
| Sub Title (in English) | |
| Keyword(1) | Ground truth |
| Keyword(2) | Locally Likely Arrangement Hashing (LLAH) |
| Keyword(3) | Camera Captured Documents |
| Keyword(4) | Perspective distortion |
| Keyword(5) | Blur |
| 1st Author's Name | Sheraz AHMED |
| 1st Author's Affiliation | German Research Center for Artificial Intelligence (DFKI)() |
| 2nd Author's Name | Koichi KISE |
| 2nd Author's Affiliation | Osaka Prefecture University |
| 3rd Author's Name | Masakazu IWAMURA |
| 3rd Author's Affiliation | Osaka Prefecture University |
| 4th Author's Name | Marcus LIWICKI |
| 4th Author's Affiliation | University of Fribourg |
| 5th Author's Name | Andreas DENGEL |
| 5th Author's Affiliation | German Research Center for Artificial Intelligence (DFKI) |
| Date | 2013-03-15 |
| Paper # | PRMU2012-204 |
| Volume (vol) | vol.112 |
| Number (no) | 495 |
| Page | pp.pp.- |
| #Pages | 6 |
| Date of Issue | |