scene-text-detection-recognition-papers

Text Detection

Title Method Architecture Year Conference Paper Code
Detecting text in natural image with connectionist text proposal network (CTPN) regression-based Faster RCNN 2016 ECCV Paper Code
Multi-oriented text detection with fully convolutional networks (MOTD) segmentation-based FCN 2017 CVPR Paper
Scene text detection via holistic, multi-channel prediction (STDH) segmentation-based FCN 2017 arXiv Paper
Detecting oriented text in natural images by linking segments (SegLink) regression-based SSD 2017 CVPR Paper Code
Single shot text detector with regional attention (SSTD) regression-based SSD 2017 ICCV Paper Code
Wordsup: Exploiting word annotations for character based text detection (Wordsup) segmentation-based FCN 2017 ICCV Paper
Textboxes: A fast text detector with a single deep neural network (Textbooks) regression-based 2017 AAAI Paper Code
East: an efficient and accurate scene text detector East) hybrid,segmentation-based FCN 2017 CVPR Paper Code
Deep direct regression for multi-oriented scene text detection (DDR) regression-based DenseBox 2017 ICCV Paper
R2CNN: Rotational region cnn for orientation robust scene text detection (R2CNN) regression-based Faster RCNN 2018 arXiv Paper
Textsnake: A flexible representation for detecting text of arbi- trary shapes (Textsnake) segmentation-based U-Net 2018 ECCV Paper
Textboxes++: A single-shot oriented scene text detector (Textboxes++) regression-based SSD 2018 TIP Paper Code
Rotation-sensitive regression for oriented scene text detection (RRD) regression-based SSD 2018 CVPR Paper
Multi-oriented scene text detection via corner localization and region segmentation (Corner Localization) segmentation-based FCN 2018 CVPR Paper Code
Pixellink: Detecting scene text via instance segmentation (Pixellink) segmentation-based FCN 2018 AAAI Paper Code
Character region awareness for text detection (CRAFT) segmentation-based U-Net 2019 CVPR Paper
Efficient and accurate arbitrary-shaped text detection with pixel aggregation network (PAN) segmentation-based FPRM+FFM 2019 ICCV Paper
Pyramid mask text detector (PMTD) hybrid Faster RCNN 2019 arXiv Paper Code
Textfield: Learning a deep direction field for irregular scene text detection (Textfield) hybrid FCN 2019 arXiv Paper
Omnidirectional scene text detection with sequential-free box discretization (BDN) hybrid Faster RCNN 2019 IJCAI Paper Code
Scene Text Detection with Supervised Pyramid Context Network(SPCNet) hybrid FPN 2019 AAAI Paper
Shape robust text detection with progressive scale expansion network (PSENet) segmentation-based FPN 2019 CVPR Paper Code
TextFuseNet: Scene Text Detection with Richer Fused Features hybrid 2020 ECCV Paper Code
Real-time Scene Text Detection with Differentiable Binarization (DB) hybrid 2020 AAAI Paper Code

Text recognition

Title Architecture Year Conference Paper Code
Robust scene text recognition with automatic rectification (RARE) Attention-based 2016 CVPR Paper
Recursive recurrent nets with attention modeling for OCR in the wild (R2AM) Attention-based 2016 CVPR Paper
STAR-Net: A spatial attention residue network for scene text recognition (STARNet) CTC-based 2016 BMVC Paper
An end-to-end trainable neural network for image-based sequence recognition and its application to scene text recognition (CRNN) CTC-based 2017 IEEE Transactions on Pattern Analysis and Machine Intelligence Paper Code
Gated recurrent convolution neural network for OCR (GRCNN) CTC-based 2017 NIPS Paper Code
Learning to read irregular text with attention mechanisms (L2RI) Attention-based 2017 IJCAI Paper
Focusing attention: Towards accurate text recognition in natural images (FAN) Attention-based 2017 ICCV Paper
Char-net: A character- aware neural network for distorted scene text recognition (Char-Net) Attention-based 2018 AAAI Paper
Aon: Towards arbitrarily-oriented text recognition Attention-based 2018 CVPR Paper Code
Edit probability for scene text recognition (EP) Attention-based 2018 CVPR Paper
Scene text recognition from two-dimensional perspective (CA-FCN) Attention-based 2018 AAAI Paper
Show, attend and read: A simple and strong baseline for irregular text recognition (SAR) Attention-based 2018 AAAI Paper Code
Rosetta: Large scale system for text detection and recognition in images (ROSETTA) CTC-based 2018 Paper
Aster: An attentional scene text recognizer with flexible rectification (ASTER) Attention-based 2018 IEEE Paper Code
Synthetically supervised feature learning for scene text recognition (SSEF) CTC-based 2018 ECCV Paper
What is wrong with scene text recognition model comparisons? dataset and model analysis (CLOVA) Attention-based 2018 ICCV Paper Code
Aggregation cross-entropy for sequence recognition (ACE) Attention-based 2019 Paper Code
Esir: End-to-end scene text recognition via iterative image rectification (ESIR) Attention-based 2019 CVPR Paper
Moran: A multi-object rectified at- tention network for scene text recognition (MORAN) Attention-based 2019 Pattern Recognition Paper Code
2D-CTC for scene text recognition (2D-CTC) 2D-CTC 2019 Paper
SCATTER: selective context attentional scene text recognizer Attention-based 2020 CVPR Paper Code
Bidirectional Scene Text Recognition with a Single Decoder (Bi-STET) Attention-based 2020 ECAI Paper Code
Towards accurate scene text recognition with semantic reasoning networks Attention-based 2020 CVPR Paper
Hamming OCR: A Locality Sensitive Hashing Neural Network for Scene Text Recognition Attention-based 2020 arXiv Paper

End-to-End approach

Title Arcitecture Year Conference Paper Code
Textboxes: A fast text detector with a single deep neural network CTC,SSD 2017 AAAI Paper Code
Deep textspotter: An end-to-end trainable scene text localization and recognition framework (Deep TextSpotter) CTC,Yolo 2017 ICCV Paper
Towards end-to-end text spotting with convolutional recurrent neural networks Attention 2017 IEEE Paper
Mask TextSpotter: An End-to-End Trainable Neural Network for Spotting Text with Arbitrary Shapes (Mask TextSpotter) CTC,R-CNN 2018 ECCV Paper Code
An end-to-end textspotter with explicit alignment and attention Attention 2018 IEEE Paper Code
FOTS: Fast oriented text spotting with a unified network (FOTS) CTC 2018 CVPR Paper Code
Textboxes++: A single-shot oriented scene text detector (TextBoxes++) CTC 2018 TIP Paper Code
Total-text: A comprehensive dataset for scene text detection and recognition (Total-Text) 2018 IEEE Paper Code
TextNet: Irregular Text Reading from Images with an End-to-End Trainable Network (TextNet) Attention 2018 ACCV Paper
Convolutional character networks (CharNet) R-CNN 2019 ICCV Paper Code
TextDragon: An End-to-End Framework for Arbitrary Shaped Text Spotting (TextDragon) CTC 2019 ICCV Paper
Towards unconstrained end-to-end text spotting 2019 ICCV Paper
Text Perceptron: Towards End-to-End Arbitrary-Shaped Text Spotting (Text Perceptron) CTC,R-CNN 2020 AAAI Paper
All You Need Is Boundary: Toward Arbitrary-Shaped Text Spotting Attention 2020 AAAI Paper
ABCNet: Real-time Scene Text Spotting with Adaptive Bezier-Curve Network (ABCNet) CTC 2020 CVPR Paper Code