preprintJul 1, 2017Closed access

Detecting Oriented Text in Natural Images by Linking Segments

Huazhong University of Science and Technology · Cornell University

Indexed incrossref

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…

Citation impact

813
total citations
FWCI
35.11
Percentile
100%
References
39
Citations per year

Authors

3

Topics & keywords

Keywords
  • Margin (machine learning)
  • Computer science
  • Convolutional neural network
  • Artificial intelligence
  • Word (group theory)
  • Benchmark (surveying)
  • Line (geometry)
  • Pattern recognition (psychology)
UN Sustainable Development Goals
  • Quality Education
No related works found for this paper.

Funding