Focal CTC Loss for Chinese Optical Character Recognition on Unbalanced Datasets

Xinjie Feng, Hongxun Yao and Shengping Zhang

Complexity, 2019, vol. 2019, 1-11

Abstract:

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.

Date: 2019
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
http://downloads.hindawi.com/journals/8503/2019/9345861.pdf (application/pdf)
http://downloads.hindawi.com/journals/8503/2019/9345861.xml (text/xml)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:hin:complx:9345861

DOI: 10.1155/2019/9345861

Access Statistics for this article

More articles in Complexity from Hindawi
Bibliographic data for series maintained by Mohamed Abdelhakeem (mohamed.abdelhakeem@hindawi.com).