AI Paper Atlas

Research map / Detection and segmentation / CNN features

Self-Organized Text Detection With Minimal Post-Processing via Border Learning

Yue Wu, Prem Natarajan

ICCV 2017 · Detection and segmentation › CNN features · approach: Arbitrary-shape scene text detection · 101 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (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
add the border class (three-class output) to the single-resolution FCN (ablation)single-res. FCN · PPT test setF-score: 0.65 -> 0.92Improved
add multi-resolution analysis to the FCN with border (ablation)FCN with border · PPT test setF-score: 0.92 -> 0.96Improved
use lightweight FCN instead of Text-Block FCN (both without border)text detector without border · PPT test setF-score: 0.65 -> 0.65No clear effect
use lightweight FCN instead of Text-Block FCN (both without border)text detector without border · PPT test setGPU decoding time (sec/img): 0.55 -> 0.24Improved
add the border class to the single-resolution FCN (ablation)single-res. FCN · PPT test setprecision: 0.61 -> 0.91Improved
add the border class to the single-resolution FCN (ablation)single-res. FCN · PPT test setrecall: 0.69 -> 0.94Improved
add multi-resolution analysis, costing decoding time (ablation)FCN with border · PPT test setGPU decoding time (sec/img): 0.25 -> 0.32Hurt

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