Focal Text: an Accurate Text Detection with Focal Loss
Lists
Only you see this
Abstract
Text detection in natural scene images is an important and popular task in the computer vision community. Due to slanted characters and blurred images in natural environments, it is a challenging task under active research. In this paper, we propose a Focal Text Detection Network (FTDN), which could be trained well without abundant data. FTDN is able to segment text region and simultaneously regress text box at pixel-level. Specifically, combined with focal loss, our method can balance positive/negative and easy/hard samples to achieve better performance. Compared with previous methods, FTDN achieves better performance in terms of text detection accuracy in natural scene. It outperforms the state-of-the-art methods on the standard ICDAR 2015 dataset with 80.9% F-measure.
BibTeX
@inproceedings{tian2018focal,
author = {Xiaowei Tian and Dao Wu and Rui Wang and Xiaochun Cao},
title = {{Focal Text: an Accurate Text Detection with Focal Loss}},
booktitle = {ICIP},
year = {2018},
doi = {10.1109/icip.2018.8451241},
}Loading related content...