Title | ||
---|---|---|
Complex image processing with less data—Document image binarization by integrating multiple pre-trained U-Net modules |
Abstract | ||
---|---|---|
•Propose a novel document binarization method by cascading pre-trained U-Nets.•Use pre-trained U-Net for solving a training image shortage problem.•Study for optimal inter-module skip-connections between U-Net modules.•Analyze the results of DIBCO images included various types of noise.•Compare all DIBCO dataset (2009–2018) and show robust performance. |
Year | DOI | Venue |
---|---|---|
2021 | 10.1016/j.patcog.2020.107577 | Pattern Recognition |
Keywords | DocType | Volume |
Convolutional neural network,U-Net,Document image binarization,DIBCO,H-DIBCO | Journal | 109 |
Issue | ISSN | Citations |
1 | 0031-3203 | 0 |
PageRank | References | Authors |
0.34 | 0 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Seokjun Kang | 1 | 0 | 0.68 |
Brian Kenji Iwana | 2 | 10 | 4.24 |
Seiichi Uchida | 3 | 790 | 105.59 |