Focal CTC Loss for Chinese Optical Character Recognition on Unbalanced Datasets
In this paper, we propose a novel deep model for unbalanced distribution Character Recognition by employing focal loss based connectionist temporal classification (CTC) function. Previous works utilize Traditional CTC to compute prediction losses. However, some datasets may consist of extremely unba...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2019-01-01
|
| Series: | Complexity |
| Online Access: | http://dx.doi.org/10.1155/2019/9345861 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | In this paper, we propose a novel deep model for unbalanced distribution Character Recognition by employing focal loss based connectionist temporal classification (CTC) function. Previous works utilize Traditional CTC to compute prediction losses. However, some datasets may consist of extremely unbalanced samples, such as Chinese. In other words, both training and testing sets contain large amounts of low-frequent samples. The low-frequent samples have very limited influence on the model during training. To solve this issue, we modify the traditional CTC by fusing focal loss with it and thus make the model attend to the low-frequent samples at training stage. In order to demonstrate the advantage of the proposed method, we conduct experiments on two types of datasets: synthetic and real image sequence datasets. The results on both datasets demonstrate that the proposed focal CTC loss function achieves desired performance on unbalanced datasets. Specifically, our method outperforms traditional CTC by 3 to 9 percentages in accuracy on average. |
|---|---|
| ISSN: | 1076-2787 1099-0526 |