Scene Text Detection
73 papers with code • 9 benchmarks • 13 datasets
Scene Text Detection is a task to detect text regions in the complex background and label them with bounding boxes.
Source: ContourNet: Taking a Further Step toward Accurate Arbitrary-shaped Scene Text Detection
Benchmarks
These leaderboards are used to track progress in Scene Text Detection
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
Libraries
Use these libraries to find Scene Text Detection models and implementationsDatasets
ICDAR 2013
MSRA-TD500
Total-Text
COCO-Text
ICDAR 2015
SCUT-CTW1500
ICDAR 2017
RCTW-17
TextOCR
Chinese Text in the Wild
Most implemented papers
EAST: An Efficient and Accurate Scene Text Detector
PaddlePaddle/PaddleOCR
•
•
CVPR 2017
Previous approaches for scene text detection have already achieved promising performances across various benchmarks.
Detecting Text in Natural Image with Connectionist Text Proposal Network
eragonruan/text-detection-ctpn
•
•
We propose a novel Connectionist Text Proposal Network (CTPN) that accurately localizes text lines in natural image.
Character Region Awareness for Text Detection
JaidedAI/EasyOCR
•
•
CVPR 2019
Scene text detection methods based on neural networks have emerged recently and have shown promising results.
Shape Robust Text Detection with Progressive Scale Expansion Network
PaddlePaddle/PaddleOCR
•
•
CVPR 2019
Due to the fact that there are large geometrical margins among the minimal scale kernels, our method is effective to split the close text instances, making it easier to use segmentation-based methods to detect arbitrary-shaped text instances.
Real-time Scene Text Detection with Differentiable Binarization
MhLiao/DB
•
•
Recently, segmentation-based methods are quite popular in scene text detection, as the segmentation results can more accurately describe scene text of various shapes such as curve text.
Shape Robust Text Detection with Progressive Scale Expansion Network
whai362/PSENet
•
•
To address these problems, we propose a novel Progressive Scale Expansion Network (PSENet), designed as a segmentation-based detector with multiple predictions for each text instance.
FOTS: Fast Oriented Text Spotting with a Unified Network
jiangxiluning/FOTS.PyTorch
•
•
CVPR 2018
Incidental scene text spotting is considered one of the most difficult and valuable challenges in the document analysis community.
ABCNet: Real-time Scene Text Spotting with Adaptive Bezier-Curve Network
aim-uofa/AdelaiDet
•
•
CVPR 2020
Our contributions are three-fold: 1) For the first time, we adaptively fit arbitrarily-shaped text by a parameterized Bezier curve.
Detecting Oriented Text in Natural Images by Linking Segments
It achieves an f-measure of 75. 0% on the standard ICDAR 2015 Incidental (Challenge 4) benchmark, outperforming the previous best by a large margin.
PixelLink: Detecting Scene Text via Instance Segmentation
Most state-of-the-art scene text detection algorithms are deep learning based methods that depend on bounding box regression and perform at least two kinds of predictions: text/non-text classification and location regression.
