IncepText: A New Inception-Text Module with Deformable PSROI Pooling for Multi-Oriented Scene Text Detection
Abstract
Incidental scene text detection, especially for multi-oriented text regions, is one of the most challenging tasks in many computer vision applications.Different from the common object detection task, scene text often suffers from a large variance of aspect ratio, scale, and orientation. To solve this problem, we propose a novel end-to-end scene text detector IncepText from an instance-aware segmentation perspective. We design a novel Inception-Text module and introduce deformable PSROI pooling to deal with multi-oriented text detection. Extensive experiments on ICDAR2015, RCTW-17, and MSRA-TD500 datasets demonstrate our method's superiority in terms of both effectiveness and efficiency. Our proposed method achieves 1st place result on ICDAR2015 challenge and the state-of-the-art performance on other datasets. Moreover, we have released our implementation as an OCR product which is available for public access.
Cite
Text
Yang et al. "IncepText: A New Inception-Text Module with Deformable PSROI Pooling for Multi-Oriented Scene Text Detection." International Joint Conference on Artificial Intelligence, 2018. doi:10.24963/IJCAI.2018/149Markdown
[Yang et al. "IncepText: A New Inception-Text Module with Deformable PSROI Pooling for Multi-Oriented Scene Text Detection." International Joint Conference on Artificial Intelligence, 2018.](https://mlanthology.org/ijcai/2018/yang2018ijcai-inceptext/) doi:10.24963/IJCAI.2018/149BibTeX
@inproceedings{yang2018ijcai-inceptext,
title = {{IncepText: A New Inception-Text Module with Deformable PSROI Pooling for Multi-Oriented Scene Text Detection}},
author = {Yang, Qiangpeng and Cheng, Mengli and Zhou, Wenmeng and Chen, Yan and Qiu, Minghui and Lin, Wei},
booktitle = {International Joint Conference on Artificial Intelligence},
year = {2018},
pages = {1071-1077},
doi = {10.24963/IJCAI.2018/149},
url = {https://mlanthology.org/ijcai/2018/yang2018ijcai-inceptext/}
}