/Scene-Text-Recognition-Recommendations

Papers, Datasets, Algorithms, SOTA for STR. Long-time Maintaining

Primary LanguagePythonMIT LicenseMIT

Scene Text Recognition Recommendations


Everything about Scene Text Recognition

SOTA Papers Datasets Code Our Framework

Contents


Checkout Our New Work!

Revisiting Scene Text Recognition: A Data Perspective



1. Papers

All Papers Can be Find Here

  • Latest Papers:
up to (2023-11-29)
up to (2023-8-11)
up to (2023-7-25)
up to (2023-7-25)
up to (2023-7-20)
up to (2023-6-1)
up to (2023-5-16)
up to (2023-3-16)
up to (2022-12-29)
up to (2022-11-1)
up to (2022-11-1)
up to (2022-9-20)
up to (2022-8-9)
up to (2022-7-24)
up to (2022-7-9)
up to (2022-5-12)

2. Datasets

All Datasets Can be Find Here

2.1 Synthetic Training Datasets

Dataset Description Examples BaiduNetdisk link
SynthText 9 million synthetic text instance images from a set of 90k common English words. Words are rendered onto nartural images with random transformations SynthText Scene text datasets(提取码:emco)
MJSynth 6 million synthetic text instances. It's a generation of SynthText. MJText Scene text datasets(提取码:emco)

2.2 Benchmarks

Dataset Description Examples BaiduNetdisk link
IIIT5k-Words(IIIT5K) 3000 test images instances. Take from street scenes and from originally-digital images IIIT5K Scene text datasets(提取码:emco)
Street View Text(SVT) 647 test images instances. Some images are severely corrupted by noise, blur, and low resolution SVT Scene text datasets(提取码:emco)
StreetViewText-Perspective(SVT-P) 639 test images instances. It is specifically designed to evaluate perspective distorted textrecognition. It is built based on the original SVT dataset by selecting the images at the sameaddress on Google Street View but with different view angles. Therefore, most text instancesare heavily distorted by the non-frontal view angle. SVTP Scene text datasets(提取码:emco)
ICDAR 2003(IC03) 867 test image instances IC03 Scene text datasets(提取码:mfir)
ICDAR 2013(IC13) 1015 test images instances IC13 Scene text datasets(提取码:emco)
ICDAR 2015(IC15) 2077 test images instances. As text images were taken by Google Glasses without ensuringthe image quality, most of the text is very small, blurred, and multi-oriented IC15 Scene text datasets(提取码:emco)
CUTE80(CUTE) 288 It focuses on curved text recognition. Most images in CUTE have acomplex background, perspective distortion, and poor resolution CUTE Scene text datasets(提取码:emco)

2.3 Other Real Datasets

Dataset Description Examples BaiduNetdisk link
COCO-Text 39K Created from the MS COCO dataset. As the MS COCO dataset is not intended to capture text. COCO contains many occluded or low-resolution texts IIIT5K Others(提取码:DLVC)
RCTW 8186 in English. RCTW is created for Reading Chinese Text in the Wild competition. We select those in english IIIT5K Others(提取码:DLVC)
Uber-Text 92K. Collecetd from Bing Maps Streetside. Many are house number, and some are text on signboards IIIT5K Others(提取码:DLVC)
Art 29K. Art is created to recognize Arbitrary-shaped Text. Many are perspective or curved texts. It also includes Totaltext and CTW1500, which contain many rotated or curved texts IIIT5K Others(提取码:DLVC)
LSVT 34K in English. LSVT is a Large-scale Streeet View Text dataset, collected from streets in China. We select those in english IIIT5K Others(提取码:DLVC)
MLT19 46K in English. MLT19 is created to recognize Multi-Lingual Text. It consists of seven languages:Arabic, Latin, Chinese, Japanese, Korean, Bangla, and Hindi. We select those in english IIIT5K Others(提取码:DLVC)
ReCTS 23K in English. ReCTS is created for the Reading Chinese Text on Signboard competition. It contains many irregular texts arranged in various layouts or written with unique fonts. We select those in english IIIT5K Others(提取码:DLVC)

3 Public Code

3.1 Frameworks

PaddleOCR (百度)

  • PaddlePaddle/PaddleOCR
  • 特性 (截取至PaddleOCR):
    • 使用百度自研深度学习框架PaddlePaddle搭建
    • PP-OCR系列高质量预训练模型,准确的识别效果
      • 超轻量PP-OCRv2系列:检测(3.1M)+ 方向分类器(1.4M)+ 识别(8.5M)= 13.0M
      • 超轻量PP-OCR mobile移动端系列:检测(3.0M)+方向分类器(1.4M)+ 识别(5.0M)= 9.4M
      • 通用PPOCR server系列:检测(47.1M)+方向分类器(1.4M)+ 识别(94.9M)= 143.4M
      • 支持中英文数字组合识别、竖排文本识别、长文本识别
      • 支持多语言识别:韩语、日语、德语、法语
      • 丰富易用的OCR相关工具组件
    • 半自动数据标注工具PPOCRLabel:支持快速高效的数据标注
      • 数据合成工具Style-Text:批量合成大量与目标场景类似的图像
      • 文档分析能力PP-Structure:版面分析与表格识别
      • 支持用户自定义训练,提供丰富的预测推理部署方案
      • 支持PIP快速安装使用
      • 可运行于Linux、Windows、MacOS等多种系统
  • 支持算法(识别):
    • CRNN
    • Rosetta
    • STAR-Net
    • RARE
    • SRN
    • NRTR

MMOCR (OpenMMLab)

  • open-mmlab/mmocr
  • 特性(截取至MMOCR):
    • MMOCR 是基于 PyTorchmmdetection 的开源工具箱,专注于文本检测,文本识别以及相应的下游任务,如关键信息提取。 它是 OpenMMLab 项目的一部分。
    • 该工具箱不仅支持文本检测和文本识别,还支持其下游任务,例如关键信息提取。
  • 支持算法(识别)
    • ABINet (CVPR'2021)
    • CRNN (TPAMI'2016)
    • MASTER (PR'2021)
    • NRTR (ICDAR'2019)
    • RobustScanner (ECCV'2020)
    • SAR (AAAI'2019)
    • SATRN (CVPR'2020 Workshop on Text and Documents in the Deep Learning Era)
    • SegOCR (Manuscript'2021)

Deep Text Recognition Benchmark (ClovaAI)


DAVAR-Lab-OCR (海康威视)

  • hikopensource/DAVAR-Lab-OCR
  • 特性:
    • 基于mmocr搭建,复现了一些算法,同时将来会用于海康自研算法开源
  • 支持算法(识别)
    • Attention(CVPR 2016)
    • CRNN(TPAMI 2017)
    • ACE(CVPR 2019)
    • SPIN(AAAI 2021)
    • RF-Learning(ICDAR 2021)

3.2. Algorithms

CRNN


ASTER

  • Tensorflow, official, 651⭐: bgshih/aster
    • 官方实现版本,使用Tensorflow
  • Pytorch, 535⭐:ayumuymk/aster.pytorch
    • Pytorch版本,准确率相较原文有明显提升

MORANv2

  • Pytorch, official, 572⭐:Canjie-Luo/MORAN_v2
    • MORAN v2版本。更加稳定的单阶段训练,更换ResNet做backbone,使用双向解码器

4. SOTAs

All the models are evaluated in a lexicon-free manner

Regular Dataset Irregular  dataset
Model Year IIIT SVT IC13(857) IC13(1015) IC15(1811) IC15(2077) SVTP CUTE
CRNN  2015 78.2 80.8 - 86.7 - - - -
ASTER(L2R)  2015 92.67 91.16 - 90.74 76.1 - 78.76 76.39
CombBest  2019 87.9 87.5 93.6 92.3 77.6 71.8 79.2 74
ESIR 2019 93.3 90.2 - 91.3 - 76.9 79.6 83.3
SE-ASTER  2020 93.8 89.6 - 92.8 80 81.4 83.6
DAN  2020 94.3 89.2 - 93.9 - 74.5 80 84.4
RobustScanner 2020 95.3 88.1 - 94.8 - 77.1 79.5 90.3
AutoSTR  2020 94.7 90.9 - 94.2 81.8 - 81.7 -
Yang et al.  2020 94.7 88.9 - 93.2 79.5 77.1 80.9 85.4
SATRN  2020 92.8 91.3 - 94.1 - 79 86.5 87.8
SRN  2020 94.8 91.5 95.5 - 82.7 - 85.1 87.8
GA-SPIN  2021 95.2 90.9 - 94.8 82.8 79.5 83.2 87.5
PREN2D  2021 95.6 94 96.4 - 83 - 87.6 91.7
Bhunia et al.  2021 95.2 92.2 - 95.5 - 84 85.7 89.7
Luo et al.  2021 95.6 90.6 - 96.0 83.9 81.4 85.1 91.3
VisionLAN  2021 95.8 91.7 95.7 - 83.7 - 86 88.5
ABINet  2021 96.2 93.5 97.4 - 86.0 - 89.3 89.2
MATRN 2021 96.7 94.9 97.9 95.8 86.6 82.9 90.5 94.1

Baek's Reimplementation Version

img