AI Paper Atlas

Research map / Image generation / Text-to-image diffusion

Content and Style Aware Generation of Text-Line Images for Handwriting Recognition

Lei Kang, Pau Riba, Marçal Rusiñol, Alícia Fornés, Mauricio Villegas

TPAMI 2021 · Image generation › Text-to-image diffusion · approach: Personalized and region-controlled generation · 71 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 generated samples (WikiText lexicon) to IAM training setHTR recognizer · IAM testCER (%): 10.46 -> 9.66Improved
use IAM lexicon instead of WikiText for generated textHTR recognizer · IAM testCER (%): 9.66 -> 9.37Improved
add data augmentation on real and generated samplesHTR recognizer · IAM testCER (%): 9.37 -> 8.62Improved
add generated samples and augmentation (proposed vs ScrabbleGAN)HTR recognizer · IAM testCER (%): 13.57 -> 8.62Improved
adapt recognizer with synthetic samples mimicking unlabeled Rimes styleHTR recognizer · Rimes testCER (%): 27.30 -> 18.19Improved
use Rimes-style instead of IAM-style synthetic adaptation dataHTR recognizer · Rimes testCER (%): 20.55 -> 18.19Improved
use recognizer trained independently instead of jointly with generatorHTR recognizer · IAM testCER (%): 16.73 -> 10.46Improved
replace VGG19 with ResNet34 convolutional layers (ablation)generator · IAM testvFID: 115.46 -> 114.39Improved
replace VGG19 with ResNet34 convolutional layers (ablation)generator · IAM testspeed (ms): 144.13 -> 136.80Improved
replace Seq2Seq recognizer with Transformer recognizer (ablation)generator · IAM text-lines (1-90 chars)vFID: 249.94 -> 114.39Improved
replace Seq2Seq recognizer with Transformer recognizer (ablation)generator · IAM words (1-10 chars)vFID: 136.51 -> 146.74Hurt
add global string encoding to local character-wise encoding (ablation)generator · IAM words (1-10 chars)vFID: 162.38 -> 146.74Improved

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