Handwritten Text Recognition On Iam Line
Métriques
Test CER
Test WER
Résultats
Résultats de performance de divers modèles sur ce benchmark
Nom du modèle | Test CER | Test WER | Paper Title | Repository |
---|---|---|---|---|
GFCN | 8.0 | 28.6 | Recurrence-free unconstrained handwritten text recognition using gated fully convolutional network | - |
TrOCR | 3.4 | - | TrOCR: Transformer-based Optical Character Recognition with Pre-trained Models | - |
HTR-VT | 4.7 | 14.9 | HTR-VT: Handwritten Text Recognition with Vision Transformer | - |
OrigamiNet-12 | 6.0 | 22.3 | OrigamiNet: Weakly-Supervised, Segmentation-Free, One-Step, Full Page Text Recognition by learning to unfold | - |
VAN | 5.0 | 16.3 | End-to-end Handwritten Paragraph Text Recognition Using a Vertical Attention Network | - |
0 of 5 row(s) selected.