Arbitrary-Oriented Scene Text Detection via Rotation Proposals
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.
Code (4)
Tasks
Computational EfficiencyRegion ProposalScene Text DetectionText DetectionSimilar Papers 제목 키워드 기반
Rotation-Sensitive Regression for Oriented Scene Text Detection
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+4R2CNN: Rotational Region CNN for Orientation Robust Scene Text Detection
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 DetectionOptimization for Arbitrary-Oriented Object Detection via Representation Invariance Loss
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+2Dynamic Anchor Learning for Arbitrary-Oriented Object Detection
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+2On the Arbitrary-Oriented Object Detection: Classification based Approaches Revisited
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