Scene Text Detection and Recognition: The Deep Learning Era
arXiv:1811.04256
Abstract
With the rise and development of deep learning, computer vision has been tremendously transformed and reshaped. As an important research area in computer vision, scene text detection and recognition has been inescapably influenced by this wave of revolution, consequentially entering the era of deep learning. In recent years, the community has witnessed substantial advancements in mindset, approach and performance. This survey is aimed at summarizing and analyzing the major changes and significant progresses of scene text detection and recognition in the deep learning era. Through this article, we devote to: (1) introduce new insights and ideas; (2) highlight recent techniques and benchmarks; (3) look ahead into future trends. Specifically, we will emphasize the dramatic differences brought by deep learning and the grand challenges still remained. We expect that this review paper would serve as a reference book for researchers in this field. Related resources are also collected and compiled in our Github repository: https://github.com/Jyouhou/SceneTextPapers.
arXiv commentThis is a pre-print of an article published in International Journal of Computer Vision. The final authenticated version will be available online at: https://doi.org/10.1007/s11263-020-01369-0
References in corpus (31)
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Distilling the Knowledge in a Neural Network
- Sequence to Sequence Learning with Neural Networks
- Semi-Supervised Classification with Graph Convolutional Networks
- Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
- Convolutional Sequence to Sequence Learning
- DSSD : Deconvolutional Single Shot Detector
- TextBoxes++: A Single-Shot Oriented Scene Text Detector
- Synthetic Data and Artificial Neural Networks for Natural Scene Text Recognition
- Robust Text Detection in Natural Scene Images
- Focusing Attention: Towards Accurate Text Recognition in Natural Images
- Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics
- R2CNN: Rotational Region CNN for Orientation Robust Scene Text Detection
- TextBoxes: A Fast Text Detector with a Single Deep Neural Network
- Born Again Neural Networks
- Rosetta: Large scale system for text detection and recognition in images
- Deep Learning for Generic Object Detection: A Survey
- Detecting Curve Text in the Wild: New Dataset and New Solution
- Scene Text Detection via Holistic, Multi-Channel Prediction
- PVANET: Deep but Lightweight Neural Networks for Real-time Object Detection
- Deep Structured Output Learning for Unconstrained Text Recognition
- Scene Text Recognition with Sliding Convolutional Character Models
- Deep Matching Prior Network: Toward Tighter Multi-oriented Text Detection
- Reading Scene Text with Attention Convolutional Sequence Modeling
- Oriented Response Networks
- ICDAR2017 Competition on Reading Chinese Text in the Wild (RCTW-17)
- Fused Text Segmentation Networks for Multi-oriented Scene Text Detection
- Chinese Text in the Wild
- Adaptive Adversarial Attack on Scene Text Recognition
- SynthText3D: Synthesizing Scene Text Images from 3D Virtual Worlds
- Deep Residual Text Detection Network for Scene Text
Cited by in corpus (24)
- MASTER: Multi-Aspect Non-local Network for Scene Text Recognition
- UnrealText: Synthesizing Realistic Scene Text Images from the Unreal World
- Text Recognition in the Wild: A Survey
- Beyond Visual Semantics: Exploring the Role of Scene Text in Image Understanding
- Text Detection and Recognition in the Wild: A Review
- Towards Unconstrained End-to-End Text Spotting
- TextScanner: Reading Characters in Order for Robust Scene Text Recognition
- Rethinking Irregular Scene Text Recognition
- Decoupled Attention Network for Text Recognition
- SCATTER: Selective Context Attentional Scene Text Recognizer
- Towards End-to-End Text Spotting in Natural Scenes
- Scene Text Image Super-Resolution in the Wild
- Curved Text Detection in Natural Scene Images with Semi- and Weakly-Supervised Learning
- All You Need Is Boundary: Toward Arbitrary-Shaped Text Spotting
- A New Perspective for Flexible Feature Gathering in Scene Text Recognition Via Character Anchor Pooling
- Character Region Attention For Text Spotting
- FedOCR: Communication-Efficient Federated Learning for Scene Text Recognition
- SAFFIRE: System for Autonomous Feature Filtering and Intelligent ROI Estimation
- Scene Text Detection with Selected Anchor
- ICDAR 2021 Competition on Integrated Circuit Text Spotting and Aesthetic Assessment
- Scene Text Recognition with Temporal Convolutional Encoder
- A Low Computational Approach for Price Tag Recognition
- Using Human Psychophysics to Evaluate Generalization in Scene Text Recognition Models
- CLEval: Character-Level Evaluation for Text Detection and Recognition Tasks