Detecting Oriented Text in Natural Images by Linking Segments

Abstract

Most state-of-the-art text detection methods are specific to horizontal Latin text and are not fast enough for real-time applications. We introduce Segment Linking (SegLink), an oriented text detection method. The main idea is to decompose text into two locally detectable elements, namely segments and links. A segment is an oriented box covering a part of a word or text line; A link connects two adjacent segments, indicating that they belong to the same word or text line. Both elements are detected densely at multiple scales by an end-to-end trained, fully-convolutional neural network. Final detections are produced by combining segments connected by links. Compared with previous methods, SegLink improves along the dimensions of accuracy, speed, and ease of training. It achieves an f-measure of 75.0% on the standard ICDAR 2015 Incidental (Challenge 4) benchmark, outperforming the previous best by a large margin. It runs at over 20 FPS on 512x512 images. Moreover, without modification, SegLink is able to detect long lines of non-Latin text, such as Chinese.

To Appear in CVPR 2017

References in corpus (5)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Fully Convolutional Networks for Semantic Segmentation
• Scene Text Detection via Holistic, Multi-Channel Prediction
• Synthetic Data for Text Localisation in Natural Images
• Multi-Oriented Text Detection with Fully Convolutional Networks

Cited by in corpus (14)

• PixelLink: Detecting Scene Text via Instance Segmentation
• WordSup: Exploiting Word Annotations for Character based Text Detection
• IncepText: A New Inception-Text Module with Deformable PSROI Pooling for Multi-Oriented Scene Text Detection
• Learning Markov Clustering Networks for Scene Text Detection
• 3D-A-Nets: 3D Deep Dense Descriptor for Volumetric Shapes with Adversarial Networks
• Scene Text Detection with Supervised Pyramid Context Network
• TextMountain: Accurate Scene Text Detection via Instance Segmentation
• Convolutional Character Networks
• FOTS: Fast Oriented Text Spotting with a Unified Network
• Curved Text Detection in Natural Scene Images with Semi- and Weakly-Supervised Learning
• AON: Towards Arbitrarily-Oriented Text Recognition
• Detecting Text in the Wild with Deep Character Embedding Network
• Correlation Propagation Networks for Scene Text Detection
• AE TextSpotter: Learning Visual and Linguistic Representation for Ambiguous Text Spotting