Detecting Oriented Text in Natural Images by Linking Segments
Top Cited Papers
- 1 July 2017
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 10636919,p. 3482-3490
- https://doi.org/10.1109/cvpr.2017.371
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.Keywords
Other Versions
This publication has 17 references indexed in Scilit:
- Real-Time Lexicon-Free Scene Text Localization and RecognitionIEEE Transactions on Pattern Analysis and Machine Intelligence, 2015
- Symmetry-based text line detection in natural scenesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2015
- Fully convolutional networks for semantic segmentationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2015
- Reading Text in the Wild with Convolutional Neural NetworksInternational Journal of Computer Vision, 2015
- Multi-Orientation Scene Text Detection with Adaptive ClusteringIEEE Transactions on Pattern Analysis and Machine Intelligence, 2015
- Orientation Robust Text Line Detection in Natural ImagesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2014
- Rich Feature Hierarchies for Accurate Object Detection and Semantic SegmentationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2014
- Text Localization in Natural Images Using Stroke Feature Transform and Text Covariance DescriptorsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2013
- Robust Text Detection in Natural Scene ImagesIEEE Transactions on Pattern Analysis and Machine Intelligence, 2013
- ICDAR 2013 Robust Reading CompetitionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2013