AI Paper Atlas

Research map / Detection and segmentation / CNN features

Verisimilar Image Synthesis for Accurate Detection and Recognition of Texts in Scenes

Fangneng Zhan, Shijian Lu, Chuhui Xue

ECCV 2018 · Detection and segmentation › CNN features · approach: Arbitrary-shape scene text detection · 111 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 semantic coherence to random embedding (ablation)synthesis, EAST on ICDAR2013 · ICDAR2013 detectionF-measure (%): 83.08 -> 84.19Improved
add saliency guidance to random embedding (ablation)synthesis, EAST on ICDAR2013 · ICDAR2013 detectionF-measure (%): 83.08 -> 84.72Improved
add adaptive text appearance to random embedding (ablation)synthesis, EAST on ICDAR2013 · ICDAR2013 detectionF-measure (%): 83.08 -> 83.40Improved
add adaptive text appearance to SC+SG (ablation)synthesis, EAST on ICDAR2013 · ICDAR2013 detectionF-measure (%): 85.94 -> 86.29Improved
add saliency guidance to SC+ATA (ablation)synthesis, EAST on ICDAR2013 · ICDAR2013 detectionF-measure (%): 85.10 -> 86.29Improved
add semantic coherence to SG+ATA (ablation)synthesis, EAST on ICDAR2013 · ICDAR2013 detectionF-measure (%): 85.72 -> 86.29Improved
add 1K random-embedding synthetic images to real data (ablation)EAST on ICDAR2013 · ICDAR2013 detectionprecision (%): 85.56 -> 84.49Hurt
increase synthetic images from 1K to 10K (ablation)EAST on ICDAR2013 · ICDAR2013 detectionF-measure (%): 86.29 -> 88.25Improved
add 10K synthetic images to real training dataEAST on ICDAR2015 · ICDAR2015 detectionF-score (%): 79.7 -> 81.9Improved
add 10K synthetic images to real training dataEAST on MSRA-TD500 · MSRA-TD500 detectionF-score (%): 73.4 -> 78.6Improved
use our synthesized images instead of Gupta et al. at 10KEAST on ICDAR2013 · ICDAR2013 detectionF-measure (%): 87.74 -> 88.25Improved
add 5M synthetic word images to real dataCRNN on ICDAR2013 recognition · ICDAR2013 recognition (no lexicon)correctly recognized words (%): 31.2 -> 87.1Improved

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