Abstract | ||
---|---|---|
In recent years, U-Net has achieved good results in various image processing tasks. However, conventional U-Nets need to be re-trained for individual tasks with enough amount of images with ground-truth. This requirement makes U-Net not applicable to tasks with small amounts of data. In this paper, we propose to use "modular" U-Nets, each of which is pre-trained to perform an existing image processing task, such as dilation, erosion, and histogram equalization. Then, to accomplish a specific image processing task, such as binarization of historical document images, the modular U-Nets are cascaded with inter-module skip connections and fine-tuned to the target task. We verified the proposed model using the Document Image Binarization Competition (DIBCO) 2017 dataset. |
Year | DOI | Venue |
---|---|---|
2019 | 10.1109/ICDAR.2019.00113 | ICDAR |
Field | DocType | Citations |
Computer vision,Dilation (morphology),Pattern recognition,Computer science,Convolutional neural network,Image processing,Artificial intelligence,Modular design,Histogram equalization,Historical document | Conference | 0 |
PageRank | References | Authors |
0.34 | 0 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Seokjun Kang | 1 | 0 | 0.34 |
Brian Kenji Iwana | 2 | 7 | 6.58 |
Seiichi Uchida | 3 | 790 | 105.59 |