Skip to content

Latest commit

 

History

History
655 lines (421 loc) · 56.8 KB

README.md

File metadata and controls

655 lines (421 loc) · 56.8 KB
Raw

Scene Text Localization & Recognition Resources

Read this institute-wise: English, 简体中文.

Read this year-wise: English, 简体中文.

Tags: [STL] (Scene Text Localization), [TR] (Text Recognition)

[STL] (Scene Text Localization) Detect text area from scene input image

[TR] (Text Recognition) Recognize text content

Last update: Sep.17 2023

1. Papers & Code

Overview

  • [2020-arxiv] Text Detection and Recognition in the Wild: A Review paper
  • [2020-arxiv] Text Recognition in the Wild: A Survey paper
  • [2020-IJCV] Scene Text Detection and Recognition: The Deep Learning Era paper
  • [2019-ICCV] What Is Wrong With Scene Text Recognition Model Comparisons? Dataset and Model Analysis paper code
  • [2016-TIP] Text Detection Tracking and Recognition in Video: A Comprehensive Survey paper
  • [2015-PAMI] Text Detection and Recognition in Imagery: A Survey paper
  • [2014-Front.Comput.Sci] Scene Text Detection and Recognition: Recent Advances and Future Trends paper

University of Oxford

  • [2020-ECCV][STL][TR] Adaptive Text Recognition through Visual Matching paper code
  • [2018-BMVC][TR] Inductive Visual Localisation: Factorised Training for Superior Generalisation paper
  • [2016-IJCV][STL][TR] Reading Text in the Wild with Convolutional Neural Networks paper demo homepage
  • [2016-CVPR][STL] Synthetic Data for Text Localisation in Natural Images paper code data
  • [2015-ICLR][TR] Deep structured output learning for unconstrained text recognition paper
  • [2015-PhD Thesis][STL] Deep Learning for Text Spotting paper code
  • [2014-ECCV][STL] Deep Features for Text Spotting paper code model
  • [2014-NIPS][TR] Synthetic Data and Artificial Neural Networks for Natural Scene Text Recognition paper homepage model

Shenzhen Institutes of Advanced Technology

  • [2018-arxiv][STL][TR] FOTS: Fast Oriented Text Spotting with a Unified Network paper
  • [2016-ECCV][STL] CTPN: Detecting Text in Natural Image with Connectionist Text Proposal Network paper code
  • [2016-CVPR][STL] Accurate Text Localization in Natural Image with Cascaded Convolutional Text Network paper
  • [2016-AAAI][STL] Reading Scene Text in Deep Convolutional Sequences paper
  • [2016-TIP][STL] Text-Attentional Convolutional Neural Networks for Scene Text Detection paper
  • [2016-TIP][STL] Text-Attentional Convolutional Neural Network for Scene Text Detection paper
  • [2014-ECCV][STL] Robust Scene Text Detection with Convolution Neural Network Induced MSER Trees paper

South China University of Technology

  • [2021-IJCV][STL] Exploring the Capacity of an Orderless Box Discretization Network for Multi-orientation Scene Text Detection paper code
  • [2021-CVPR][STL] Fourier Contour Embedding for Arbitrary-Shaped Text Detection paper
  • [2021-CVPR][TR][STL] Implicit Feature Alignment: Learn To Convert Text Recognizer to Text Spotter paper code
  • [2020-CVPR][TR] Learn to Augment: Joint Data Augmentation and Network Optimization for Text Recognition paper code
  • [2020-AAAI][STL][TR] Decoupled Attention Network for Text Recognition paper
  • [2020-CVPR][STL][TR] ABCNet: Real-time Scene Text Spotting with Adaptive Bezier-Curve Network paper code
  • [2020-IJCV][TR] Separating Content from Style Using Adversarial Learning for Recognizing Text in the Wild paper
  • [2019-Pattern Recognition][TR] A Multi-Object Rectified Attention Network for Scene Text Recognition paper code
  • [2019-CVPR][TR] Aggregation Cross-Entropy for Sequence Recognition paper code
  • [2019-arxiv][STL] Exploring the Capacity of an Orderless Box Discretization Network for Multi-orientation Scene Text Detection paper code code
  • [2019-CVPR][STL] Tightness-Aware Evaluation Protocol for Scene Text Detection paper
  • [2018-AAAI][STL] Feature Enhancement Network: A Refined Scene Text Detector paper
  • [2017-arXiv][STL] Detecting Curve Text in the Wild: New Dataset and New Solution paper
  • [2020-arxiv][TR] Adaptive Embedding Gate for Attention-Based Scene Text Recognition paper
  • [2017-PAMI][TR] Learning Spatial-Semantic Context with Fully Convolutional Recurrent Network for Online Handwritten Chinese Text Recognition paper
  • [2017-CVPR][STL] Deep Matching Prior Network: Toward Tighter Multi-oriented Text Detection paper
  • [2016-arXiv][STL] DeepText:A Unified Framework for Text Proposal Generation and Text Detection in Natural Images paper
  • [2016-IEEE Transactions on Multimedia][STL] A Convolutional Neural Network Based Chinese Text Detection Algorithm Via Text Structure Modeling paper

Fudan University

  • [2022-AAAI][TR] Text Gestalt: Stroke-Aware Scene Text Image Super-resolution paper code
  • [2023-MM][TR] Chinese Character Recognition with Augmented Character Profile Matching paper code
  • [2023-ICCV][TR] Chinese Text Recognition with A Pre-Trained CLIP-Like Model Through Image-IDS Aligning paper code
  • [2023-arxiv][STL][TR] Weakly-Supervised Text Instance Segmentation paper code
  • [2023-IJCAI][TR] Orientation-Independent Chinese Text Recognition in Scene Images paper
  • [2023-IJCAI][TR] TPS++: Attention-Enhanced Thin-Plate Spline for Scene Text Recognition paper code
  • [2023-IJCAI][STL][TR] Towards Accurate Video Text Spotting with Text-wise Semantic Reasoning paper code
  • [2022-MM][TR] Chinese Character Recognition with Augmented Character Profile Matching paper code
  • [2022-WACV][TR] Robustly Recognizing Irregular Scene Text by Rectifying Principle Irregularities paper
  • [2021-IJCAI][TR] Zero-Shot Chinese Character Recognition with Stroke-Level Decomposition paper code
  • [2022-IJCAI][TR] C3-STISR: Scene Text Image Super-resolution with Triple Clues paper [code][https://github.com/zhaominyiz/C3-STISR]
  • [2021-CVPR][TR] Scene Text Telescope: Text-Focused Scene Image Super-Resolution paper
  • [2020-arxiv][TR] Text Recognition in Real Scenarios with a Few Labeled Samples paper
  • [2018-CVPR][TR] Edit Probability for Scene Text Recognition paper
  • [2017-arXiv][STL] Arbitrary-Oriented Scene Text Detection via Rotation Proposals paper code

Huazhong University of Science and Technology

  • [2021-CVPR][STL][TR] Scene Text Retrieval via Joint Text Detection and Similarity Learning paper code
  • [2021-CVPR][STL] MOST: A Multi-Oriented Scene Text Detector With Localization Refinement paper
  • [2020-ECCV][TR] AutoSTR: Efficient Backbone Search for Scene Text Recognition paper
  • [2020-AAAI][STL][TR] All You Need Is Boundary: Toward Arbitrary-Shaped Text Spotting paper
  • [2020-AAAI][STL] Real-time Scene Text Detection with Differentiable Binarization paper code
  • [2020-ECCV][STL][TR] Mask TextSpotter V3: Segmentation Proposal Network for Robust Scene Text Spotting paper code
  • [2019-PAMI][TR] ASTER: An Attentional Scene Text Recognizer with Flexible Rectification paper code
  • [2019-AAAI][TR] Scene Text Recognition from Two-Dimensional Perspective paper
  • [2019-PAMI][STL] Gliding vertex on the horizontal bounding box for multi-oriented object detection paper code
  • [2019-ICCV][TR] Symmetry-Constrained Rectification Network for Scene Text Recognition paper
  • [2018-arxiv][STL] TextField: Learning A Deep Direction Field for Irregular Scene Text Detection paper code
  • [2018-ECCV][TR][STL] Mask TextSpotter: An End-to-End Trainable Neural Network for Spotting Text with Arbitrary Shapes paper
  • [2018-ICIP][STL] Feature Fusion Network for Scene Text Detection paper
  • [2018-CVPR][STL] Multi-Oriented Scene Text Detection via Corner Localization and Region Segmentation paper
  • [2018-CVPR][STL] Rotation-sensitive Regression for Oriented Scene Text Detection paper
  • [2018-TIP][STL] TextBoxes++: A Single-Shot Oriented Scene Text Detector paper code
  • [2017-AAAI][STL] TextBoxes: A Fast TextDetector with a Single Deep Neural Network paper code
  • [2017-CVPR][STL] Detecting Oriented Text in Natural Images by Linking Segments paper code
  • [2016-CVPR][TR] Robust scene text recognition with automatic rectification paper
  • [2016-arXiv][STL] Scene Text Detection via Holistic, Multi-Channel Prediction paper
  • [2016-CVPR][STL] Multi-oriented text detection with fully convolutional networks paper
  • [2015-PAMI][TR] An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition paper code code
  • [2014-CVPR][TR] Strokelets: A Learned Multi-Scale Representation for Scene Text Recognition paper

Universitat Autònoma de Barcelona

  • [2019-ICCV][STL][TR] Scene Text Visual Question Answering paper
  • [2018-ECCV][STL] Single Shot Scene Text Retrieval paper
  • [2017-arXiv][STL] Improving Text Proposal for Scene Images with Fully Convolutional Networks paper
  • [2016-arXiv][STL] TextProposals: a Text-specific Selective Search Algorithm for Word Spotting in the Wild paper code
  • [2015-ICDAR][STL] Object Proposals for Text Extraction in the Wild paper code
  • [2014-PAMI][TR] Word Spotting and Recognition with Embedded Attributes paper homepage code

Stanford University

  • [2012-ICPR][TR] End-to-End Text Recognition with Convolutional Neural Networks paper code SVHN Dataset
  • [2012-PhD Thesis][TR] End-to-End Text Recognition with Convolutional Neural Networks paper

Seoul National University

  • [2017-AAAI][STL][TR] Detection and Recognition of Text Embedding in Online Images via Neural Context Models paper

Megvii Technology Inc: Face++

  • [2020-CVPR][TR] On Vocabulary Reliance in Scene Text Recognition paper
  • [2020-AAAI][STL][TR] TextScanner: Reading Characters in Order for Robust Scene Text Recognition paper
  • [2017-CVPR][STL] EAST: An Efficient and Accurate Scene Text Detector paper code code with improvement

Institute of Automation, Chinese Academy of Sciences

  • [2020-IJCV][STL][TR] Residual Dual Scale Scene Text Spotting by Fusing Bottom-Up and Top-Down Processing paper
  • [2019-CVPR][TR] Sequence-to-Sequence Domain Adaptation Networkfor Robust Text Image Recognition paper
  • [2019-ICCV][STL][TR] TextDragon: An End-to-End Framework for Arbitrary Shaped Text Spotting paper
  • [2018-arxiv][TR] NRTR: A No-Recurrence Sequence-to-Sequence Model For Scene Text Recognition paper code
  • [2018-arxiv][TR] SCAN: Sliding Convolutional Attention Network for Scene Text Recognition paper code
  • [2018-arxiv][TR] Recurrent Calibration Network for Irregular Text Recognition paper
  • [2017-arxiv][TR] Scene Text Recognition with Sliding Convolutional Character Models paper code
  • [2017-arXiv][STL] Deep Direct Regression for Multi-Oriented Scene Text Detection paper
  • [2017-IAPR][STL] Scene Text Detection with Novel Superpixel Based Character Candidate Extraction paper

University of California, San Diego

  • [2016-CVPR][TR] Recursive Recurrent Nets with Attention Modeling for OCR in the Wild paper

University of California, Santa Cruz

  • [2017-arXiv][STL] Cascaded Segmentation-Detection Networks for Word-Level Text Spotting paper

Cornell University

  • [2016-arXiv][STL][TR] COCO-Text: Dataset and Benchmark for Text Detection and Recognition in Natural Images paper

Pennsylvania State University

  • [2017-WACV][STL] TextContourNet: A Flexible and Effective Framework for Improving Scene Text Detection Architecture With a Multi-Task Cascade paper
  • [2016-PhD Thesis][STL] Context Modeling for Semantic Text Matching and Scene Text Detection paper

University of Science and Technology Beijing

  • [2021-ICCV][STL] Adaptive Boundary Proposal Network for Arbitrary Shape Text Detection paper code
  • [2020-CVPR][STL] Deep Relational Reasoning Graph Network for Arbitrary Shape Text Detection paper
  • [2017-arxiv][TR] AdaDNNs: Adaptive Ensemble of Deep Neural Networks for Scene Text Recognition paper
  • [2016-IJCAI][STL] Scene Text Detection in Video by Learning Locally and Globally paper
  • [2014-PAMI][TR] Robust Text Detection in Natural Scene Images paper

Pohang University of Science and Technology

  • [2016-CVPR][STL] CannyText Detector: Fast and Robust Scene Text Localization Algorithm paper

École d'Ingénieurs en Informatique

  • [2016-IJDAR][STL] TextCatcher: a method to detect curved and challenging text in natural scenes paper

České vysoké učení technické v Praze. Czech Technical University

  • [2018-ACCV][STL][TR] E2E-MLT - an Unconstrained End-to-End Method for Multi-Language Scene Text paper code
  • [2017-ICCV][STL][TR] Deep TextSpotter: An End-to-End Trainable Scene Text Localization and Recognition Framework peper code
  • [2015-PAMI][STL][TR] Real-time Lexicon-free Scene Text Localization and Recognition paper
  • [2015-ICCV][STL] FASText: Efficient unconstrained scene text detector paper code
  • [2012-CVPR][STL][TR] Real-time scene text localization and recognition paper code

Google Inc

  • [2019-ICCV][STL] Towards Unconstrained End-to-End Text Spotting paper
  • [2013-ICCV][STL][TR] Photo OCR: Reading Text in Uncontrolled Conditions paper

Microsoft Inc

  • [2010-CVPR][STL] SWT: Detecting Text in Natural Scenes with Stroke Width Transform paper code

Samsung R&D Institute China

  • [2019-CVPR][STL] Arbitrary Shape Scene Text Detection With Adaptive Text Region Representation paper
  • [2017-arXiv][STL] R2CNN: Rotational Region CNN for Orientation Robust Scene Text Detection paper
  • [2017-IAPR][STL] Deep Residual Text Detection Network for Scene Text paper

Vicarious FPC Inc

  • [2016-NIPS][TR] Generative Shape Models: Joint Text Recognition and Segmentation with Very Little Training Data paper

Chinese State Key Laboratory of Management and Control for Complex Systems

  • [2013-CVPR][TR] Scene Text Recognition using Part-based Tree-structured Character Detection paper

Stanford University

  • [2012-ICPR][TR] End-to-End Text Recognition with CNN paper code

Visual Computing Department, Institute for Infocomm Research

  • [2017-ICCV][STL] WeText: Scene Text Detection under Weak Supervision paper

University of Florida

  • [2017-ICCV][STL] Single Shot Text Detector with Regional Attention paper code

University of Southern California

  • [2017-ICCV][STL] Self-organized Text Detection with Minimal Post-processing via Border Learning paper

Hikvision Research Institute

  • [2021-AAAI][STL][TR] MANGO: A Mask Attention Guided One-Stage Scene Text Spotter paper
  • [2020-AAAI][STL][TR] Text Perceptron: Towards End-to-End Arbitrary-Shaped Text Spotting paper
  • [2018-CVPR][TR] AON: Towards Arbitrarily-Oriented Text Recognition paper code
  • [2017-ICCV][TR] Focusing Attention: Towards Accurate Text Recognition in Natural Images paper

University of Adelaide

  • [2019-AAAI][TR] Show, Attend and Read: A Simple and Strong Baseline for Irregular Text Recognition paper code
  • [2017-ICCV][STL][TR] Towards End-to-end Text Spotting with Convolutional Recurrent Neural Networks paper

City University of New York

  • [2017-CVPR][STL] Unambiguous Text Localization and Retrieval for Cluttered Scenes paper

The University of Hong Kong

  • [2020-ECCV][STL][TR] AE TextSpotter: Learning Visual and Linguistic Representation for Ambiguous Text Spotting paper
  • [2018-AAAI][TR] Char-Net: A Character-Aware Neural Network for Distorted Scene Text paper

Zhejiang University

  • [2021-TIP][STL][TR] FREE: A Fast and Robust End-to-End Video Text Spotter paper
  • [2020-arxiv][TR] Refined Gate: A Simple and Effective Gating Mechanism for Recurrent Units paper
  • [2018-AAAI][STL] PixelLink: Detecting Scene Text via Instance Segmentation paper

University of Potsdam

  • [2018-AAAI][STL][TR] SEE: Towards Semi-Supervised End-to-End Scene Text Recognition paper code

Arizona State Unviversity

  • [2018-AAAI][TR] SqueezedText: A Real-time Scene Text Recognition by Binary Convolutional Encoder-decoder Network paper

Stevens Institute of Technology

  • [2018-CVPR][STL] Geometry-Aware Scene Text Detection with Instance Transformation Network paper

Nanyang Technological University

  • [2020-IJCV][STL] Bottom-Up Scene Text Detection with Markov Clustering Networks paper
  • [2020-AAAI][STL][TR] GTC: Guided Training of CTC Towards Efficient and Accurate Scene Text Recognition paper
  • [2019-ICCV][STL][TR] GA-DAN: Geometry-Aware Domain Adaptation Network for Scene Text Detection and Recognition paper
  • [2019-CVPR][STL] ESIR: End-To-End Scene Text Recognition via Iterative Image Rectification paper
  • [2019-CVPR][STL] Towards Robust Curve Text Detection With Conditional Spatial Expansion paperLiu_Towards_Robust_Curve_Text_Detection_With_Conditional_Spatial_Expansion_CVPR_2019_paper.html)
  • [2018-ECCV][STL] Verisimilar Image Synthesis for Accurate Detection and Recognition of Texts in Scenes paper
  • [2018-ECCV][STL] Accurate Scene Text Detection through Border Semantics Awareness and Bootstrapping paper
  • [2018-ECCV][STL] Using Object Information for Spotting Text paper
  • [2018-CVPR][STL] Learning Markov Clustering Networks for Scene Text Detection paper

Alibaba Group

  • [2018-ICPR][STL][TR] A Novel Integrated Framework for Learning both Text Detection and Recognition paper
  • [2018-IJCAI][STL] IncepText: A New Inception-Text Module with Deformable PSROI Pooling for Multi-Oriented Scene Text Detection paper

Chinese Academy of Sciences

  • [2020-CVPR][STL][TR] Multi-Modal Graph Neural Network for Joint Reasoning on Vision and Scene Text paper
  • [2018-ICIP][STL] Focal Text: An Accurate Text Detection With Focal Loss paper
  • [2018-ICIP][STL] Dense Chained Attention Network for Scene Text Recognition paper

University of Cambridge

  • [2018-ECCV][STL] Synthetically Supervised Feature Learning for Scene Text Recognition paper

Peking University

  • [2021-NIPS][TR] CentripetalText: An Efficient Text Instance Representation for Scene Text Detection paper code
  • [2020-ICASSP][TR] A New Perspective for Flexible Feature Gathering in Scene Text Recognition Via Character Anchor Pooling paper
  • [2020-ICASSP][STL] All you need is a second look: Towards Tighter Arbitrary shape text detection paper
  • [2019-WACV][STL] Mask R-CNN with Pyramid Attention Network for Scene Text Detection paper
  • [2018-ECCV][STL] TextSnake: A Flexible Representation for Detecting Text of Arbitrary Shapes paper code

SenseTime Research

  • [2021-WACV][STL] Disentangled Contour Learning for Quadrilateral Text Detection paper code
  • [2020-ECCV][TR] RobustScanner: Dynamically Enhancing Positional Clues for Robust Text Recognition paper
  • [2020-ECCV][TR] Scene Text Image Super-resolution in the wild paper
  • [2019-arxiv][STL] Pyramid Mask Text Detector paper
  • [2019-ICCV][STL] Geometry Normalization Networks for Accurate Scene Text Detection paper
  • [2018-BMVC][STL] Boosting up Scene Text Detectors with Guided CNN paper

Naver Clova AI Research

  • [2020-ECCV][STL] Character Region Attention For Text Spotting paper
  • [2019-CVPR][STL][TR] Character Region Awareness for Text Detection paper code

Baidu

  • [2020-arxiv][STL][TR] PP-OCR: A Practical Ultra Lightweight OCR System paper
  • [2019-ICCV][STL][TR] Chinese Street View Text: Large-Scale Chinese Text Reading With Partially Supervised Learning paper
  • [2019-CVPR][STL] Look More Than Once: An Accurate Detector for Text of Arbitrary Shapes paper
  • [2018-arxiv][STL] Detecting Text in the Wild with Deep Character Embedding Network paper
  • [2018-ACCV][STL][TR] TextNet: Irregular Text Reading from Images with an End-to-End Trainable Network paper

University of Adelaide

  • [2018-CVPR][STL][TR] An End-to-End TextSpotter with Explicit Alignment and Attention paper code

Nanjing University

  • [2020-BMVC][TR] Robust Scene Text Recognition Through Adaptive Image Enhancement paper
  • [2019-ICCV][STL] Efficient and Accurate Arbitrary-Shaped Text Detection With Pixel Aggregation Network paper code
  • [2019-CVPR][STL] Shape Robust Text Detection With Progressive Scale Expansion Network paper code

The Chinese University of Hong Kong

  • [2022-AAAI][TR] Context-based Contrastive Learning for Scene Text Recognition paper
  • [2019-CVPR][STL] Learning Shape-Aware Embedding for Scene Text Detection paper

Malong Technologies

  • [2019-ICCV][STL][TR] Convolutional Character Networks paper code

University of Rochester

  • [2019-ICCV][TR] Large-Scale Tag-Based Font Retrieval With Generative Feature Learning paper

Facebook AI Research

  • [2021-CVPR][STL][TR] TextOCR: Towards Large-Scale End-to-End Reasoning for Arbitrary-Shaped Scene Text paper code
  • [2020-CVPR][STL][TR] Iterative Answer Prediction with Pointer-Augmented Multimodal Transformers for TextVQA paper
  • [2018-arxiv][STL] Improving Rotated Text Detection with Rotation Region Proposal Networks paper

University of Marlyand

  • [2020-WACV][TR] Adapting Style and Content for Attended Text Sequence Recognition paper

Penta-AI

  • [2020-WACV][STL] It’s All About The Scale - Efficient Text Detection Using Adaptive Scaling paper

Central China Normal University

  • [2020-ECCV][STL][TR] PlugNet: Degradation Aware Scene Text Recognition Supervised by a Pluggable Super-Resolution Unit paper

Tencent

  • [2022-AAAI][TR] Perceiving Stroke-Semantic Context: Hierarchical Contrastive Learning for Robust Scene Text Recognition paper
  • [2020-arxiv][STL] PuzzleNet: Scene Text Detection by Segment Context Graph Learning paper
  • [2020-AAAI][STL][TR] Accurate Structured-Text Spotting for Arithmetical Exercise Correction paper
  • [2019-arxiv][TR] 2D Attentional Irregular Scene Text Recognizer paper code

Tsinghua University

  • [2023-IJCAI][TR] Towards Robust Scene Text Image Super-resolution via Explicit Location Enhancement paper code
  • [2021-CVPR][STL] Primitive Representation Learning for Scene Text Recognition paper
  • [2020-ECCV][STL] Sequential Deformation for Accurate Scene Text Detection paper

University of Science and Technology of China

  • [2023-IJCAI][TR] Linguistic More: Taking a Further Step toward Effcient and Accurate Scene Text Recognition paper code
  • [2021-ICCV][TR] From Two to One: A New Scene Text Recognizer With Visual Language Modeling Network paper
  • [2021-CVPR][STL] Read Like Humans: Autonomous, Bidirectional and Iterative Language Modeling for Scene Text Recognition paper code
  • [2020-CVPR][STL] ContourNet: Taking a Further Step Toward Accurate Arbitrary-Shaped Scene Text Detection paper code
  • [2020-arxiv][TR] Focus-Enhanced Scene Text Recognition with Deformable Convolutions paper code
  • [2018-Pattern Recognition][STL] TextMountain: Accurate Scene Text Detection via Instance Segmentation paper

University of Electronic Science and Technology of China

  • [2020-CVPR][TR] What Machines See Is Not What They Get: Fooling Scene Text Recognition Models With Adversarial Text Images paper

Indian Statistical Institute

  • [2020-CVPR][STL][TR] STEFANN: Scene Text Editor Using Font Adaptive Neural Network paper

Institute of Information Engineering, Chinese Academy of Sciences

  • [2021-CVPR][STL] Progressive Contour Regression for Arbitrary-Shape Scene Text Detection paper code
  • [2020-CVPR][TR] SEED: Semantics Enhanced Encoder-Decoder Framework for Scene Text Recognition paper
  • [2020-ICPR][TR] Gaussian Constrained Attention Network for Scene Text Recognition paper
  • [2020-arxiv][STL] Self-Training for Domain Adaptive Scene Text Detection paper
  • [2019-ICDAR][STL] Curved Text Detection in Natural Scene Images with Semi- and Weakly-Supervised Learning paper
  • [2019-BMVC][TR] Text Recognition using local correlationpaper

University of Chinese Academy of Sciences

  • [2020-CVPR][STL][TR] Towards Accurate Scene Text Recognition With Semantic Reasoning Networks paper

Amazon

  • [2020-CVPR][STL] SCATTER: Selective Context Attentional Scene Text Recognizer paper

Heritage Institute of Technology

  • [2020-ICIP][STL] Scale-invariant Multi-oriented Text Detection in Wild Scene Images paper

Indian Institute of Technology

  • [2020-arxiv][STL] NENET: An Edge Learnable Network for Link Prediction in Scene Text paper

Xidian University

  • [2021-AAAI][STL][TR] PGNet: Real-time Arbitrarily-Shaped Text Spotting with Point Gathering Network paper code
  • [2020-ICASSP][STL] Efficient Scene Text Detection with Textual Attention Tower paper
  • [2019-ACM-MM][STL] A Single-Shot Arbitrarily-Shaped Text Detector based on Context Attended Multi-Task Learning paper

Tongji University

  • [2019-AAAI][STL] Scene Text Detection with Supervised Pyramid Context Network paper code

Harbin Institute of Technology

Shanghai Jiao Tong University

  • [2018-ICPR][STL] Fused Text Segmentation Networks for Multi-oriented Scene Text Detection paper

Ping An Property & Casualty Insurance

  • [2020-arxiv][TR] Hamming OCR: A Locality Sensitive Hashing Neural Network for Scene Text Recognition paper

Hefei University of Technology

  • [2020-arxiv][TR] Fast Dense Residual Network: Enhancing Global Dense Feature Flow for Text Recognition paper

Beihang University

  • [2020-arxiv][TR] A Feasible Framework for Arbitrary-Shaped Scene Text Recognition paper [code](https: //github.com/zhang0jhon/AttentionOCR)

Boston University

  • [2020-arxiv][TR] Deep Neural Network for Semantic-based Text Recognition in Images paper

Carnegie Mellon University

  • [2019-ICDAR][TR] Rethinking Irregular Scene Text Recognition paper code

Northwestern Polytechnical University

  • [2019-CVPR][STL][TR] Towards End-to-End Text Spotting in Natural Scenes paper

VinAI Research

  • [2021-CVPR][STL] Dictionary-Guided Scene Text Recognition paper code

University of Tokyo

  • [2021-CVPR][TR] What if We Only Use Real Datasets for Scene Text Recognition? Toward Scene Text Recognition With Fewer Labels paper code

University of Surrey

  • [2021-ICCV][TR] Towards the Unseen: Iterative Text Recognition by Distilling from Errors paper
  • [2021-ICCV][TR] Joint Visual Semantic Reasoning: Multi-Stage Decoder for Text Recognition paper
  • [2021-CVPR][TR] MetaHTR: Towards Writer-Adaptive Handwritten Text Recognition paper

The Technion – Israel Institute of Technology

  • [2021-CVPR][TR] Sequence-to-Sequence Contrastive Learning for Text Recognition paper

University of Illinois at Urbana-Champaign

  • [2021-CVPR][TR] Rethinking Text Segmentation: A Novel Dataset and a Text-Specific Refinement Approach paper code

National Laboratory of Pattern Recognition

  • [2021-CVPR][STL] Semantic-Aware Video Text Detection paper

Shenzhen University

  • [2021-CVPR][STL][TR] Self-Attention Based Text Knowledge Mining for Text Detection paper code

University of the Philippines

  • [2021-ICDAR][TR] Vision Transformer for Fast and Efficient Scene Text Recognition paper 'code'

Beijing Jiaotong University

  • [2022-IJCAI][TR] SVTR: Scene Text Recognition with a Single Visual Model paper code

Wuhan University

  • [2022-AAAI][TR] Visual Semantics Allow for Textual Reasoning Better in Scene Text Recognition paper code

Helsing AI

  • [2022-WACV][TR] One-shot Compositional Data Generation for Low Resource Handwritten Text Recognition paper

Purdue University

  • [2023-WACV][TR] Seq-UPS: Sequential Uncertainty-aware Pseudo-label Selection for Semi-Supervised Text Recognition paper

2. Datasets

SCUT-CTW1500 2018

Task: text location(with different style) and recognition

download

Total Text Dataset 2017

1,555 images with more than 3 different text orientations: Horizontal, Multi-Oriented, and Curved, one of a kind

Task: text location(with different style) and recognition

download

PowerPoint Text Detection and Recognition Dataset 2017

21,384 images, 21,384+ text instances

Task: text location and recognition

download

COCO-Text (Computer Vision Group, Cornell) 2016

63,686 images, 173,589 text instances, 3 fine-grained text attributes.

Task: text location and recognition

download

Synthetic Word Dataset (Oxford, VGG) 2014

9 million images covering 90k English words

Task: text recognition, segmantation

download

The Street View House Number Dataset (SVHN) 2012

Real-world street view number image with its position and classification tags.

Task: number location detection, text recognition

download

IIIT 5K-Words 2012

5000 images from Scene Texts and born-digital (2k training and 3k testing images)

Each image is a cropped word image of scene text with case-insensitive labels

Task: text recognition

download

StanfordSynth(Stanford, AI Group) 2012

Small single-character images of 62 characters (0-9, a-z, A-Z)

Task: text recognition

download

MSRA Text Detection 500 Database (MSRA-TD500) 2012

500 natural images(resolutions of the images vary from 1296x864 to 1920x1280)

Chinese, English or mixture of both

Task: text detection

Street View Text (SVT) 2010

350 high resolution images (average size 1260 × 860) (100 images for training and 250 images for testing)

Only word level bounding boxes are provided with case-insensitive labels

Task: text location

KAIST Scene_Text Database 2010

3000 images of indoor and outdoor scenes containing text

Korean, English (Number), and Mixed (Korean + English + Number)

Task: text location, segmantation and recognition

Chars74k 2009

Over 74K images from natural images, as well as a set of synthetically generated characters

Small single-character images of 62 characters (0-9, a-z, A-Z)

Task: text recognition

ICDAR Benchmark Datasets

Dataset Description Competition Paper
ICDAR 2017 over 173,589 labeled text regions in over 63,686 images paper link
ICDAR 2015 1000 training images and 500 testing images paper link
ICDAR 2013 229 training images and 233 testing images paper link
ICDAR 2011 229 training images and 255 testing images paper link
ICDAR 2005 1001 training images and 489 testing images paper link
ICDAR 2003 181 training images and 251 testing images(word level and character level) paper link

3. Competitions

4. Online OCR Service

Name Description
Tesseract OCR API，free
Online OCR API，free
Free OCR API，free
New OCR API，free
ABBYY FineReader Online No API，Not free
Super Online Transfer Tools (Chinese) API，free
Online Chinese Recognition API，free

5. Blogs