【持续更新】文本识别与检测资源17-19汇总
2019:CVPR
其中研究文本检测的最多，共 7 篇，包括已经非常知名的PSENet，还有最近异常火爆的CRAFT。
文本识别 4 篇，其中华南理工大学的 Aggregation Cross-Entropy 代码已经开源，其不仅适用于文本数据，序列数据识别均可参考。
检测
- 利用条件空间扩展实现鲁棒弯曲文本检测
南洋理工大学、阿德莱德大学
Towards Robust Curve Text Detection With Conditional Spatial Expansion
Zichuan Liu, Guosheng Lin, Sheng Yang, Fayao Liu, Weisi Lin, Wang Ling Goh
字符区域感知的文本检测，不仅利用字符本身特征还利用字符之间的关系。在MSRA-TD500数据集上目前是最好的算法。
Clova AI Research, NAVER Corp
Character Region Awareness for Text Detection
Youngmin Baek, Bado Lee, Dongyoon Han, Sangdoo Yun, Hwalsuk Lee
https://github.com/clovaai/CRAFT-pytorch
自适应文本区域表示，用于任意形状的场景文本检测，在5个文本检测数据集上都达到了state-ofthe-art。
三星中国研究院、中科院自动化所、中科院大学、韩国三星研究院
- Arbitrary Shape Scene Text Detection With Adaptive Text Region Representation
Xiaobing Wang, Yingying Jiang, Zhenbo Luo, Cheng-Lin Liu, Hyunsoo Choi, Sungjin Kim
形状感知嵌入学习用于场景文本检测
香港中文大学、约翰霍普金斯大学、腾讯优图实验室
Learning Shape-Aware Embedding for Scene Text Detection
Zhuotao Tian, Michelle Shu, Pengyuan Lyu, Ruiyu Li, Chao Zhou, Xiaoyong Shen, Jiaya Jia
- 渐近扩展网络，用于形状鲁棒的文本检测
南京大学、同济大学、南京理工大学、Momenta、旷视科技
Shape Robust Text Detection With Progressive Scale Expansion Network
Wenhai Wang, Enze Xie, Xiang Li, Wenbo Hou, Tong Lu, Gang Yu, Shuai Shao
https://github.com/whai362/PSENet
- 一种迭代的不断提精的高精度任意形状文本检测方法，在多个数据集达到了state-of-the-art。
百度、厦门大学
Look More Than Once: An Accurate Detector for Text of Arbitrary Shapes
Chengquan Zhang, Borong Liang, Zuming Huang, Mengyi En, Junyu Han, Errui Ding, Xinghao Ding
提出场景文本检测结果度量的新协议，更加以有利于进一步识别为导向，更加注重检测结果的完整性（Completeness）、紧凑性（Compactness）、细腻度（Tightness-aware）
华南理工大学
Tightness-Aware Evaluation Protocol for Scene Text Detection
Yuliang Liu, Lianwen Jin, Zecheng Xie, Canjie Luo, Shuaitao Zhang, Lele Xie
https://github.com/Yuliang-Liu/TIoU-metric
识别
提出一种聚合交叉熵损失函数，用于序列数据识别，可有效替换CTC+注意力机制，实现简单、计算快速、存储要求低、方便替换CTC。
华南理工大学
Aggregation Cross-Entropy for Sequence Recognition
Zecheng Xie, Yaoxiong Huang, Yuanzhi Zhu, Lianwen Jin, Yuliang Liu, Lele Xie
https://github.com/summerlvsong/Aggregation-Cross-Entropy
数字文档中关键字检索的深度特征方法，高效、存储要求低。
NCSR “Demokritos”、希腊国立雅典理工大学、希腊约阿尼纳大学
An Alternative Deep Feature Approach to Line Level Keyword Spotting
George Retsinas, Georgios Louloudis, Nikolaos Stamatopoulos, Giorgos Sfikas, Basilis Gatos
通过迭代的图像校正进行端到端的场景文本识别
南洋理工大学
ESIR: End-To-End Scene Text Recognition via Iterative Image Rectification
Fangneng Zhan, Shijian Lu
https://github.com/fnzhan/ESIR
序列到序列的域适应网络，用于鲁棒文本图像识别
中科院自动化所、中科院大学、电子科技大学、浙江大学、阿凡题人工智能研究院
Sequence-To-Sequence Domain Adaptation Network for Robust Text Image Recognition
Yaping Zhang, Shuai Nie, Wenju Liu, Xing Xu, Dongxiang Zhang, Heng Tao Shen
2017-2018：ECCV + CVPR + ICCV +AAAI
1.检测
水平文本
Shangxuan Tian——【ICCV2017】WeText_Scene Text Detection under Weak Supervision
Shitala Prasad——【ECCV2018】Using Object Information for Spotting Text
XiangBai——【AAAI2017】TextBoxes_A Fast Text Detector with a Single Deep Neural Network
Sheng Zhang——【AAAI2018】Feature Enhancement Network_A Refined Scene Text Detector
倾斜文本
ChengLin Liu——【ICCV2017】Deep Direct Regression for Multi-Oriented Scene Text Detection
Chuhui Xue——【ECCV2018】Accurate Scene Text Detection through Border Semantics Awareness and Bootstrapping
Cong Yao——【CVPR2017】EAST_An Efficient and Accurate Scene Text Detector
Dafang He——【CVPR2017】Multi-Scale FCN With Cascaded Instance Aware Segmentation for Arbitrary Oriented Word Spotting in the Wild
Dan Deng——【AAAI2018】PixelLink_Detecting Scene Text via Instance Segmentation
Fangfang Wang——【CVPR2018】Geometry-Aware Scene Text Detection With Instance Transformation Network
Han Hu——【ICCV2017】WordSup_Exploiting Word Annotations for Character based Text Detection
Lianwen Jin——【CVPR2017】Deep Matching Prior Network_Toward Tighter Multi-oriented Text Detection
Pan He——【ICCV2017】Single Shot Text Detector With Regional Attention
XiangBai——【CVPR2017】Detecting Oriented Text in Natural Images by link Segments
XiangBai——【CVPR2018】Multi-Oriented Scene Text Detection via Corner Localization and Region Segmentation
XiangBai——【CVPR2018】Rotation-Sensitive Regression for Oriented Scene Text Detection
Yingli Tian——【CVPR2017】Unambiguous Text Localization and Retrieval for Cluttered Scenes
Yue Wu——【ICCV2017】Self-Organized Text Detection With Minimal Post-Processing via Border Learning
Zichuang Liu——【CVPR2018】Learning Markov Clustering Networks for Scene Text Detection
曲线文本
Shangbang Long——【ECCV2018】TextSnake_A Flexible Representation for Detecting Text of Arbitrary Shapes
2.识别
Wei Liu——【AAAI2018】Char-Net_A Character-Aware Neural Network for Distorted Scene Text Recognition
Yang Liu——【ECCV2018】Synthetically Supervised Feature Learning for Scene Text Recognition
Zhanzhan Cheng——【CVPR2018】AON Towards Arbitrarily-Oriented Text Recognition
Zhanzhan Cheng——【CVPR2018】Edit Probability for Scene Text Recognition
Zhanzhan Cheng——【ICCV2017】Focusing Attention_Towards Accurate Text Recognition in Natural Images
Zichuan Liu——【AAAI2018】SqueezedText_A Real-time Scene Text Recognition by Binary Convolutional
3.检测+识别
Christian Bartz——【AAAI2018】SEE_Towards Semi-Supervised End-to-End Scene Text Recognition
Chulmoo Kang——【AAAI2017】Detection and Recognition of Text Embedded in Online Images via Neural Context Models
Chunhua Shen——【ICCV2017】Towards End-to-end Text Spotting with Convolutional Recurrent
Fangneng Zhan——【ECCV2018】Verisimilar Image Synthesis for Accurate Detection and Recognition of Texts in Scenes
Lluis Gomez——【ECCV2018】Single Shot Scene Text Retrieval
Lukas Neumann——【ICCV2017】Deep TextSpotter_An End-to-End Trainable Scene Text Localization and Recognition Framework
Weilin Huang——【CVPR2018】An End-to-End TextSpotter With Explicit Alignment and Attention
XiangBai——【ECCV2018】Mask TextSpotter An End-to-End Trainable Neural Network for Spotting Text with Arbitrary Shapes
XiangBai——【PAMI2018】ASTER_An Attentional Scene Text Recognizer with Flexible Rectification
YuQiao——【CVPR2018】FOTS Fast Oriented Text Spotting With a Unified Network
其他CV会议期刊
2017年
Daitao Xing——【2017】ArbiText_Arbitrary-Oriented Text Detection in Unconstrained Scene
Dena Bazazian——【2017】Improving Text Proposals for Scene Images with Fully Convolutional Networks
Fan Jiang——【2017】Deep Scene Text Detection with Connected Component Proposals
Jiaqi Ma——【2017】Arbitrary-Oriented Scene Text Detection via Rotation Proposals
Lluis Gomez——【PR2017】TextProposals_A text-specific selective search algorithm for word spotting in the wild
Siyang Qin——【2017】Cascaded Segmentation-Detection Networks for Word-Level TextSpotting
Suman Ghosh——【2017】R-PHOC_Segmentation-Free Word Spotting using CNN
Xiangyu Zhu——【ICDAR2017】Deep Residual Text Detection Network for Scene Text
Yingying Jiang——【2017】R2CNN_Rotational Region CNN for Orientation Robust Scene Text Detection
Yuchen Dai——【2017】Fused Text Segmentation Networks for Multi-Oriented Scene Text Detection
Yuliang Liu——【2017】Detecting Curve Text in the Wild_New Dataset and New Solution(曲线文本)
2018年
Chunhua Shen——【2018】Correlation Propagation Networks for Scene Text Detection
Dafang He——【2018】TextContourNet_a Flexible and Effective Framework for Improving Scene Text
Jun Du——【ICPR2018】Sliding Line Point Regression for Shape Robust Scene Text Detection
Qiangpeng Yang——【IJCAI2018】IncepText_A New Inception-Text Module with Deformable PSROI Pooling for Multi-Oriented Scene Text Detection
QiYuan——【2018】A Single Shot Text Detector with Scale-adaptive Anchors
XiangBai——【2018TIP】TextBoxes++_A Single-Shot Oriented Scene Text Detector
XiangBai——【PAMI2018】ASTER_An Attentional Scene Text Recognizer with Flexible Rectification
XiangLi——【2018】Shape Robust Text Detection with Progressive Scale Expansion Network
Yu Qiao——【BMVC2018】Boosting up Scene Text Detectors with Guided CNN
Zhuoyao Zhong——【2018】An Anchor-Free Region Proposal Network for Faster R-CNN based Text Detection Approaches
OCR资源推荐
https://github.com/chongyangtao/Awesome-Scene-Text-Recognition