Scene Text Recognition On Icdar2013

Métriques

Accuracy

Résultats

Résultats de performance de divers modèles sur ce benchmark

Nom du modèle	Accuracy	Paper Title	Repository
DPAN	97.7	Look Back Again: Dual Parallel Attention Network for Accurate and Robust Scene Text Recognition
TextScanner	92.9	TextScanner: Reading Characters in Order for Robust Scene Text Recognition	-
CRNN	86.7	An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition
SVTR-L (Large)	97.2	SVTR: Scene Text Recognition with a Single Visual Model
SAR	91.0	Show, Attend and Read: A Simple and Strong Baseline for Irregular Text Recognition
CDistNet (Ours)	97.67	CDistNet: Perceiving Multi-Domain Character Distance for Robust Text Recognition
SIGA_T	97.8	Self-supervised Implicit Glyph Attention for Text Recognition
MATRN	97.9	Multi-modal Text Recognition Networks: Interactive Enhancements between Visual and Semantic Features
PARSeq	98.4±0.2	Scene Text Recognition with Permuted Autoregressive Sequence Models
S-GTR	97.8	Visual Semantics Allow for Textual Reasoning Better in Scene Text Recognition
SVTR-B (Base)	97.1	SVTR: Scene Text Recognition with a Single Visual Model
SEED	92.8	SEED: Semantics Enhanced Encoder-Decoder Framework for Scene Text Recognition
CLIP4STR-L	98.5	CLIP4STR: A Simple Baseline for Scene Text Recognition with Pre-trained Vision-Language Model	-
DAN	93.9	Decoupled Attention Network for Text Recognition
MGP-STR	98.5	Multi-Granularity Prediction for Scene Text Recognition
SVTR-S (Small)	95.7	SVTR: Scene Text Recognition with a Single Visual Model
CLIP4STR-L*	99.42	An Empirical Study of Scaling Law for OCR
SRN	95.5	Towards Accurate Scene Text Recognition with Semantic Reasoning Networks
STAR-Net	89.1	Star-net: A spatial attention residue network for scene text recognition.
DiffusionSTR	97.1	DiffusionSTR: Diffusion Model for Scene Text Recognition	-

0 of 38 row(s) selected.