atlas

Research map / Detection and segmentation / CNN features

Canny Text Detector: Fast and Robust Scene Text Localization Algorithm

CVPR 2016 · Detection and segmentation › CNN features · approach: Arbitrary-shape scene text detection · 121 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 double-threshold classification and hysteresis tracking to retain connected weak text candidatesCanny Text Detector · ICDAR 2013 RRC Challenge 2Hmean: 75.89% -> 82.17%Helped
Use ER candidates rather than MSER candidatesCanny Text Detector candidate extraction · ICDAR 2011 test setCharacter-level recall: 53.9% -> 95.1%Helped
Apply non-maximum suppression to ER candidatesCanny Text Detector candidate extraction · ICDAR 2011 test setNumber of candidates: 6,051,331 -> 629,932Helped
Use the full detection pipeline rather than ERs after NMS aloneCanny Text Detector · ICDAR 2011 test setCharacter-level recall: 95.1% -> 87.4%Hurt
Use Canny Text Detector instead of Tian et al. [32]Scene text localization · Multilingual test setHmean: 81.4 -> 93.3Helped
Use Canny Text Detector instead of Tian et al. [32]Scene text localization · Multilingual test setRecall: 78.4 -> 93.5Helped

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