Scene Text Detection and Recognition: The Deep Learning Era

By Shangbang Long, Xin He, Cong Yao. 2018

502 citations recorded by the source corpus.

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 inevitably influenced by this wave of revolution, consequentially entering the era of deep learning. In recent years, the community has witnessed substantial advancements in mindset, methodology 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 remaining grand challenges. We expect that this review paper would serve as a reference book for researchers in this field. Related resources are also collected in our Github repository (https://github.com/Jyouhou/SceneTextPapers).

Subfields: Computer Vision and Pattern Recognition, Natural Language Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

1. Xiang Bai
2. Cong Yao
3. Minghui Liao
4. Xin He
5. Zhaoyi Wan
6. Mingkun Yang
7. Lianwen Jin
8. Yongchao Xu

In Natural Language Processing

1. Minghui Liao
2. Xiang Bai
3. Mingkun Yang
4. Lianwen Jin
5. Cong Yao
6. Xin He
7. Canjie Luo
8. Song Bai

Citations in the corpus

• All You Need Is Boundary: Toward Arbitrary-Shaped Text Spotting (2019, background): “(Liu et al. 2018; Li, Wang, and Shen 2017; He et al. 2018; Busta et al. 2017) share a common idea: text region features are extracted for subsequent recognizer.”
• Symmetry-Constrained Rectification Network for Scene Text Recognition (2019, background): “Scene text reading [60, 32, 59, 54, 53, 36, 35] is an important, active research area in computer vision, which can be applied to a wide range of real-world applications, such as self-driving cars, assistant position systems, and guide board recognition [43].”
• Handwritten Optical Character Recognition (OCR): A Comprehensive Systematic Literature Review (SLR) (2020, background): “This is a complex problem to solve as a system for such a scenario needs to deal with background clutters, variable illumination condition, variable camera angles, distorted characters and variable writing styles [213].”
• Real-Time Scene Text Detection With Differentiable Binarization and Adaptive Scale Fusion (2022, background): “READING text in scene images [36] is of great importance in both academia and industry due to its abundant real-world applications, including office automation,”
• Decoupled Attention Network for Text Recognition (2019, methodology): “Connectionist temporal classification (CTC) (Graves et al. 2006) and attention mechanism (Bahdanau, Cho, and Bengio 2015) are two most popular methods, among them attention mechanism shows significant better performance and has been studied frequently in recent years (Long, He, and Yao 2018).”