ReLaText: Exploiting Visual Relationships for Arbitrary-Shaped Scene Text Detection with Graph Convolutional Networks
Preprint
Abstract
We introduce a new arbitrary-shaped text detection approach named ReLaText by formulating text detection as a visual relationship detection problem. To demonstrate the effectiveness of this new formulation, we start from using a "link" relationship to address the challenging text-line grouping problem firstly. The key idea is to decompose text detection into two subproblems, namely detection of text primitives and prediction of link relationships between nearby text primitive pairs. Specifically, an anchor-free region proposal network based text detector is first used to detect text primitives of different scales from different feature maps of a feature pyramid network, from which a text primitive graph is constructed by linking each pair of nearby text primitives detected from a same feature map with an edge. Then, a Graph Convolutional Network (GCN) based link relationship prediction module is used to prune wrongly-linked edges in the text primitive graph to generate a number of disjoint subgraphs, each representing a detected text instance. As GCN can effectively leverage context information to improve link prediction accuracy, our GCN based text-line grouping approach can achieve better text detection accuracy than previous text-line grouping methods, especially when dealing with text instances with large inter-character or very small inter-line spacings. Consequently, the proposed ReLaText achieves state-of-the-art performance on five public text detection benchmarks, namely RCTW-17, MSRA-TD500, Total-Text, CTW1500 and DAST1500.Keywords
All Related Versions
This publication has 70 references indexed in Scilit:
- An anchor-free region proposal network for Faster R-CNN-based text detection approachesInternational Journal on Document Analysis and Recognition (IJDAR), 2019
- Detecting Text in the Wild with Deep Character Embedding Network2019
- TextSnake: A Flexible Representation for Detecting Text of Arbitrary Shapes2018
- Graph R-CNN for Scene Graph Generation2018
- Graph embedding techniques, applications, and performance: A surveyKnowledge-Based Systems, 2018
- Visual Relationship Detection with Language Priors2016
- Detecting Text in Natural Image with Connectionist Text Proposal Network2016
- TextCatcher: a method to detect curved and challenging text in natural scenesInternational Journal on Document Analysis and Recognition (IJDAR), 2016
- Reading Text in the Wild with Convolutional Neural NetworksInternational Journal of Computer Vision, 2015
- A Method for Text Localization and Recognition in Real-World Images2011