The anchor mechanism of Faster R-CNN and SSD framework is considered not
effective enough to scene text detection, which can be attributed to its IoU
based matching criterion between anchors and ground-truth boxes. In order to
better enclose scene text instances of various shapes, it requires to design
anchors of various scales, aspect ratios and even orientations manually, which
makes anchor-based methods sophisticated and inefficient. In this paper, we
propose a novel anchor-free region proposal network (AF-RPN) to replace the
original anchor-based RPN in the Faster R-CNN framework to address the above
problem. Compared with a vanilla RPN and FPN-RPN, AF-RPN can get rid of
complicated anchor design and achieve higher recall rate on large-scale
COCO-Text dataset. Owing to the high-quality text proposals, our Faster R-CNN
based two-stage text detection approach achieves state-of-the-art results on
ICDAR-2017 MLT, ICDAR-2015 and ICDAR-2013 text detection benchmarks when using
single-scale and single-model (ResNet50) testing only.
%0 Generic
%1 citeulike:14594249
%A xxx,
%D 2018
%K detection ocr rcnn
%T An Anchor-Free Region Proposal Network for Faster R-CNN based Text Detection Approaches
%U http://arxiv.org/abs/1804.09003
%X The anchor mechanism of Faster R-CNN and SSD framework is considered not
effective enough to scene text detection, which can be attributed to its IoU
based matching criterion between anchors and ground-truth boxes. In order to
better enclose scene text instances of various shapes, it requires to design
anchors of various scales, aspect ratios and even orientations manually, which
makes anchor-based methods sophisticated and inefficient. In this paper, we
propose a novel anchor-free region proposal network (AF-RPN) to replace the
original anchor-based RPN in the Faster R-CNN framework to address the above
problem. Compared with a vanilla RPN and FPN-RPN, AF-RPN can get rid of
complicated anchor design and achieve higher recall rate on large-scale
COCO-Text dataset. Owing to the high-quality text proposals, our Faster R-CNN
based two-stage text detection approach achieves state-of-the-art results on
ICDAR-2017 MLT, ICDAR-2015 and ICDAR-2013 text detection benchmarks when using
single-scale and single-model (ResNet50) testing only.
@misc{citeulike:14594249,
abstract = {{The anchor mechanism of Faster R-CNN and SSD framework is considered not
effective enough to scene text detection, which can be attributed to its IoU
based matching criterion between anchors and ground-truth boxes. In order to
better enclose scene text instances of various shapes, it requires to design
anchors of various scales, aspect ratios and even orientations manually, which
makes anchor-based methods sophisticated and inefficient. In this paper, we
propose a novel anchor-free region proposal network (AF-RPN) to replace the
original anchor-based RPN in the Faster R-CNN framework to address the above
problem. Compared with a vanilla RPN and FPN-RPN, AF-RPN can get rid of
complicated anchor design and achieve higher recall rate on large-scale
COCO-Text dataset. Owing to the high-quality text proposals, our Faster R-CNN
based two-stage text detection approach achieves state-of-the-art results on
ICDAR-2017 MLT, ICDAR-2015 and ICDAR-2013 text detection benchmarks when using
single-scale and single-model (ResNet50) testing only.}},
added-at = {2019-02-27T22:23:29.000+0100},
archiveprefix = {arXiv},
author = {xxx},
biburl = {https://www.bibsonomy.org/bibtex/2e69dcbc226ba3566a124ae64ec0768bf/nmatsuk},
citeulike-article-id = {14594249},
citeulike-linkout-0 = {http://arxiv.org/abs/1804.09003},
citeulike-linkout-1 = {http://arxiv.org/pdf/1804.09003},
day = 24,
eprint = {1804.09003},
interhash = {da4e57bae50a9668a1e28e01d4fbc535},
intrahash = {e69dcbc226ba3566a124ae64ec0768bf},
keywords = {detection ocr rcnn},
month = apr,
posted-at = {2018-05-25 13:06:48},
priority = {0},
timestamp = {2019-02-27T22:23:29.000+0100},
title = {{An Anchor-Free Region Proposal Network for Faster R-CNN based Text Detection Approaches}},
url = {http://arxiv.org/abs/1804.09003},
year = 2018
}