Scene Text Detection and Recognition: The Deep Learning Era

TL;DR

This survey reviews the transformative impact of deep learning on scene text detection and recognition, highlighting recent advancements, benchmarks, and future challenges in the field.

Contribution

It provides a comprehensive summary of major changes, techniques, and benchmarks in scene text detection and recognition driven by deep learning, along with insights and future directions.

Findings

Significant performance improvements due to deep learning techniques

Emergence of new benchmarks and datasets for evaluation

Identification of grand challenges remaining in the field

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.