Article ID | Journal | Published Year | Pages | File Type |
---|---|---|---|---|
6864300 | Neurocomputing | 2018 | 40 Pages |
Abstract
In this paper, a novel neural network architecture is proposed to rectify text images with mild assumptions. A new dataset of text images is collected to verify our model. We explored the capability of deep neural network in learning geometric transformation and found the model are sensitive to the text image without explicit supervised segmentation information. Experiments show the architecture proposed can restore planar transformations with wonderful robustness and effectiveness.
Related Topics
Physical Sciences and Engineering
Computer Science
Artificial Intelligence
Authors
Chengzhe Yan, Jie Hu, Changshui Zhang,