Arbitrary-Oriented Scene Text Detection via Rotation Proposals
Authors:
- Hao YeHYHao Ye
- Yingbin ZhengYZYingbin Zheng
Preprint
Abstract
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 is 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 orientation. The Rotation Region-of-Interest (RRoI) pooling layer is proposed to project arbitrary-oriented proposals to the feature map for a text region classifier. The whole framework is built upon region proposal based architecture, which ensures the computational efficiency of the arbitrary-oriented text detection comparing 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.Keywords
All Related Versions
This publication has 31 references indexed in Scilit:
- Detecting Text in Natural Image with Connectionist Text Proposal Network2016
- Reading Text in the Wild with Convolutional Neural NetworksInternational Journal of Computer Vision, 2015
- A robust arbitrary text detection system for natural scene imagesExpert Systems with Applications, 2014
- Deep Features for Text Spotting2014
- Robust Scene Text Detection with Convolution Neural Network Induced MSER Trees2014
- Selective Search for Object RecognitionInternational Journal of Computer Vision, 2013
- A Method for Text Localization and Recognition in Real-World Images2011
- Word Spotting in the Wild2010
- ICDAR 2003 robust reading competitions: entries, results, and future directionsInternational Journal on Document Analysis and Recognition (IJDAR), 2005
- Text information extraction in images and video: a surveyPattern Recognition, 2004