paper-with-me

홈 › Papers

Arbitrary-Oriented Scene Text Detection via Rotation Proposals

2017-03-03 · Jianqi Ma, Weiyuan Shao, Hao Ye, Li Wang, Hong Wang, Yingbin Zheng, xiangyang xue

This paper introduces a novel rotation-based framework for arbitrary-oriented text detection in natural scene images. We present the Rotation Region Proposal Networks (RRPN), which are designed to generate inclined proposals with text orientation angle information. The angle information is then adapted for bounding box regression to make the proposals more accurately fit into the text region in terms of the orientation. The Rotation Region-of-Interest (RRoI) pooling layer is proposed to project arbitrary-oriented proposals to a feature map for a text region classifier. The whole framework is built upon a region-proposal-based architecture, which ensures the computational efficiency of the arbitrary-oriented text detection compared with previous text detection systems. We conduct experiments using the rotation-based framework on three real-world scene text detection datasets and demonstrate its superiority in terms of effectiveness and efficiency over previous approaches.

📄 PDF Abstract BibTeX arXiv:1703.01086

Code (4)

mjq11302010044/RRPN 공식 구현 pytorch
LUCKMOONLIGHT/SLRDet pytorch
hongzhenwang/RRPN-revise
kanuore/RRPN

Tasks

Computational EfficiencyRegion ProposalScene Text DetectionText Detection

Similar Papers 제목 키워드 기반

Rotation-Sensitive Regression for Oriented Scene Text Detection

2018-03-14 · CVPR 2018 6 · Minghui Liao, Zhen Zhu, Baoguang Shi, Gui-Song Xia 외

Text in natural images is of arbitrary orientations, requiring detection in terms of oriented bounding boxes. Normally, a multi-oriented text detector often involves two key tasks: 1) text presence detection, which is a …

ClassificationGeneral Classificationobject-detectionObject Detection+4

R2CNN: Rotational Region CNN for Orientation Robust Scene Text Detection

2017-06-29 · Yingying Jiang, Xiangyu Zhu, Xiaobing Wang, Shuli Yang 외

In this paper, we propose a novel method called Rotational Region CNN (R2CNN) for detecting arbitrary-oriented texts in natural scene images. The framework is based on Faster R-CNN [1] architecture. First, we use the Reg…

Region ProposalScene Text DetectionText Detection

Optimization for Arbitrary-Oriented Object Detection via Representation Invariance Loss

2021-03-22 · Qi Ming, Lingjuan Miao, Zhiqiang Zhou, Xue Yang 외

Arbitrary-oriented objects exist widely in natural scenes, and thus the oriented object detection has received extensive attention in recent years. The mainstream rotation detectors use oriented bounding boxes (OBB) or q…

Objectobject-detectionObject DetectionObject Detection In Aerial Images+2

Dynamic Anchor Learning for Arbitrary-Oriented Object Detection

2020-12-08 · Qi Ming, Zhiqiang Zhou, Lingjuan Miao, Hongwei Zhang 외

Arbitrary-oriented objects widely appear in natural scenes, aerial photographs, remote sensing images, etc., thus arbitrary-oriented object detection has received considerable attention. Many current rotation detectors u…

Multi-Oriented Scene Text DetectionObjectobject-detectionObject Detection In Aerial Images+2

On the Arbitrary-Oriented Object Detection: Classification based Approaches Revisited

2020-03-12 · ECCV 2020 8 · Xue Yang, Junchi Yan

Arbitrary-oriented object detection has been a building block for rotation sensitive tasks. We first show that the boundary problem suffered in existing dominant regression-based rotation detectors, is caused by angular …

ClassificationGeneral Classificationobject-detectionObject Detection+3