Name
Title | ||
|---|---|---|
Binarization of degraded document images based on hierarchical deep supervised network. |
Abstract | ||
|---|---|---|
•We propose a supervised binarization method based on the deep supervised networks.•The multi-scale deep supervised network for binarization has not been reported yet.•A hierarchical architecture is designed to distinguish text from background noises.•Different feature levels are dealt by the multi-scale architecture.•The performance results are considerably better than state-of-the-art methods. |
Year | DOI | Venue |
|---|---|---|
2018 | 10.1016/j.patcog.2017.08.025 | Pattern Recognition |
Keywords | Field | DocType |
Document image binarization,Convolutional neural network,Document analysis | Computer vision,Document analysis,Architecture,Pattern recognition,Computer science,Binary image,Robustness (computer science),Pixel,Artificial intelligence,NASA Deep Space Network | Journal |
Volume | Issue | ISSN |
74 | C | 0031-3203 |
Citations | PageRank | References |
9 | 0.46 | 22 |
Authors | ||
4 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Quang Nhat Vo | 1 | 9 | 0.46 |
| Soo-Hyung Kim | 2 | 191 | 49.03 |
| Hyungjeong Yang | 3 | 455 | 47.05 |
| Gueesang Lee | 4 | 208 | 52.71 |