Scene Text Recognition
121 papers with code • 15 benchmarks • 27 datasets
See Scene Text Detection for leaderboards in this task.
Benchmarks
These leaderboards are used to track progress in Scene Text Recognition
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
Libraries
Use these libraries to find Scene Text Recognition models and implementations
ICDAR 2013
COCO-Text
ICDAR 2003
SVT
TextOCR
RCTW-17
CUTE80
IIIT5k
Most implemented papers
SEE: Towards Semi-Supervised End-to-End Scene Text Recognition
Bartzi/see
•
•
Detecting and recognizing text in natural scene images is a challenging, yet not completely solved task.
Pedestrian-Synthesis-GAN: Generating Pedestrian Data in Real Scene and Beyond
yueruchen/Pedestrian-Synthesis-GAN
•
•
The results show that our framework can smoothly synthesize pedestrians on background images of variations and different levels of details.
On Recognizing Texts of Arbitrary Shapes with 2D Self-Attention
Scene text recognition (STR) is the task of recognizing character sequences in natural scenes.
A Feasible Framework for Arbitrary-Shaped Scene Text Recognition
Deep learning based methods have achieved surprising progress in Scene Text Recognition (STR), one of classic problems in computer vision.
SCATTER: Selective Context Attentional Scene Text Recognizer
phantrdat/cvpr20-scatter-text-recognizer
•
•
CVPR 2020
The first attention step re-weights visual features from a CNN backbone together with contextual features computed by a BiLSTM layer.
Towards Accurate Scene Text Recognition with Semantic Reasoning Networks
PaddlePaddle/PaddleOCR
•
•
CVPR 2020
Scene text image contains two levels of contents: visual texture and semantic information.
SEED: Semantics Enhanced Encoder-Decoder Framework for Scene Text Recognition
Pay20Y/SEED
•
•
CVPR 2020
Scene text recognition is a hot research topic in computer vision.
Arabic Scene Text Recognition in the Deep Learning Era: Analysis on A Novel Dataset
Therefore, we use our new dataset to evaluate the problem of Arabic scene text recognition from three perspectives: (1) using deep learning techniques and studying their suitability for Arabic scene text recognition, where we identify essential components required for the model to obtain good performance; (2) identifying Arabic text challenges that differ from Latin text and require special attention; (3) investigating a bilingual model that concurrently deals with Arabic and English words, since Arabic text is usually found along with other languages.
Look Back Again: Dual Parallel Attention Network for Accurate and Robust Scene Text Recognition
To tackle this issue, in this paper, we propose a dual parallel attention network (DPAN), in which a newly designed parallel context attention module (PCAM) is cascaded with the original PPAM, using linguistic contextual information to compensate for the information inconsistency between queries and keys.
TrOCR: Transformer-based Optical Character Recognition with Pre-trained Models
microsoft/unilm
•
•
Text recognition is a long-standing research problem for document digitalization.
