AI Paper Atlas

Research map / Detection and segmentation / CNN features

Detecting Oriented Text in Natural Images by Linking Segments

CVPR 2017 · Detection and segmentation › CNN features · approach: Arbitrary-shape scene text detection · 821 citations (OpenAlex)

Check your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Use segment-and-link detection instead of the strongest listed baselineICDAR 2015 text detection · ICDAR 2015 Incidental TextF-measure: 64.8 -> 75.0Helped
Use segment-and-link detection instead of the strongest listed baselineMSRA-TD500 text detection · MSRA-TD500F-measure: 76 -> 77Helped
Use segment-and-link detection instead of the strongest listed baselineMSRA-TD500 text detection · MSRA-TD500FPS: $\sim$1.61 -> 8.9Helped
Use segment-and-link detection instead of Tian et al.ICDAR 2013 text detection · ICDAR 2013F-measure: 87.7 -> 85.3Hurt
Use segment-and-link detection instead of Tian et al.ICDAR 2013 text detection · ICDAR 2013FPS: 7.1 -> 20.6Helped
Use segment linking for text with very large character spacingSegLink · MSRA-TD500detection successHurt
Use the current rectangle-producing combination algorithm for curved textSegLink · MSRA-TD500detection successHurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy