EAST: An Efficient and Accurate Scene Text Detector

@article{Zhou2017EASTAE,
  title={EAST: An Efficient and Accurate Scene Text Detector},
  author={Xinyu Zhou and Cong Yao and He Wen and Yuzhi Wang and Shuchang Zhou and Weiran He and Jiajun Liang},
  journal={2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  year={2017},
  pages={2642-2651}
}
  • Xinyu Zhou, C. Yao, Jiajun Liang
  • Published 11 April 2017
  • Computer Science
  • 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Previous approaches for scene text detection have already achieved promising performances across various benchmarks. [] Key Method The pipeline directly predicts words or text lines of arbitrary orientations and quadrilateral shapes in full images, eliminating unnecessary intermediate steps (e.g., candidate aggregation and word partitioning), with a single neural network. The simplicity of our pipeline allows concentrating efforts on designing loss functions and neural network architecture. Experiments on…

Figures and Tables from this paper

A Hierarchical Scene Text Detector Concerning Hard Examples
TLDR
This work proposes a hierarchical scene text detector concerning hard examples based on the Fully Convolutional Networks (FCNs), and the proposed detector HST-DHE has stronger robustness in multi-scale and multi-direction natural scene images.
Compact and Accurate Scene Text Detector
TLDR
This paper proposes a new efficient model for text detection, namely Compact and Accurate Scene Text detector (CAST), which consists of MobileNetV2 as a backbone and balanced decoder that is efficient and effective.
Efficient and Accurate Arbitrary-Shaped Text Detection With Pixel Aggregation Network
TLDR
This paper proposes an efficient and accurate arbitrary-shaped text detector, termed Pixel Aggregation Network (PAN), which is equipped with a low computational-cost segmentation head and a learnable post-processing.
Scene Text Detection and Localization using Fully Convolutional Network.
  • M. Mukhiddinov
  • Computer Science
    2019 International Conference on Information Science and Communications Technologies (ICISCT)
  • 2019
TLDR
A robust yet simple pipeline that produces accurate and fast text detection in natural scene images and quickly predicts text of random orientations in full-color images, discarding redundant intermediate stages, with a single neural network is introduced.
Comprehensive Studies for Arbitrary-shape Scene Text Detection
TLDR
This paper carefully examine and analyze the inconsistent settings, and proposes a unified framework for the bottom-up based scene text detection methods, which ensures the consistent settings for non-core modules and mainly investigates the representations of describing arbitrary-shape scene texts.
MOST: A Multi-Oriented Scene Text Detector with Localization Refinement
TLDR
A new algorithm for scene text detection is proposed, which puts forward a set of strategies to significantly improve the quality of text localization and achieves state-of-the-art or competitive performance on various standard benchmarks for text detection while keeping a fast running speed.
Sequential Deformation for Accurate Scene Text Detection
TLDR
This paper proposes a novel sequential deformation method to effectively model the line-shape of scene text and demonstrates that the proposed method has outperformed previous state-of-the-art methods.
A Fast Scene Text Detector Using Knowledge Distillation
TLDR
This paper presents an end-to-end trainable deep model, which can effectively and efficiently locate multi-oriented scene text and outperforms the most state-of-the-art methods.
Scene Text Detection with Supervised Pyramid Context Network
TLDR
A supervised pyramid context network (SPCNET) is proposed to precisely locate text regions while suppressing false positives in scene text detection, which is based on Feature Pyramid Network (FPN) and instance segmentation.
Towards Accurate Scene Text Detection with Bidirectional Feature Pyramid Network
TLDR
A new Fully Convolutional One-Stage Object Detection (FCOS)-based text detection method that can robustly detect multioriented and multilingual text from natural scene images in a per pixel prediction approach and applies the Bidirectional Feature Pyramid Network (BiFPN) as the backbone network, enhancing the model learning capacity and increasing the receptive field.
...
...

References

SHOWING 1-10 OF 55 REFERENCES
Scene Text Detection via Holistic, Multi-Channel Prediction
TLDR
This work proposes to localize text in a holistic manner, by casting scene text detection as a semantic segmentation problem, and demonstrates that the proposed algorithm substantially outperforms previous state-of-the-art approaches.
Synthetic Data for Text Localisation in Natural Images
TLDR
The relation of FCRN to the recently-introduced YOLO detector, as well as other end-to-end object detection systems based on deep learning, are discussed.
Text Flow: A Unified Text Detection System in Natural Scene Images
TLDR
The proposed unified scene text detection system, namely Text Flow, is proposed by utilizing the minimum cost (min-cost) flow network model and it outperforms the state-of-the-art methods on all three datasets with much higher recall and F-score.
Robust Scene Text Detection with Convolution Neural Network Induced MSER Trees
TLDR
A novel framework to tackle the problem of distinguishing texts from background components by leveraging the high capability of convolutional neural network (CNN), capable of learning high-level features to robustly identify text components from text-like outliers.
Detecting texts of arbitrary orientations in natural images
  • C. Yao, X. Bai, Wenyu Liu, Yi Ma, Z. Tu
  • Computer Science
    2012 IEEE Conference on Computer Vision and Pattern Recognition
  • 2012
TLDR
A system which detects texts of arbitrary orientations in natural images using a two-level classification scheme and two sets of features specially designed for capturing both the intrinsic characteristics of texts to better evaluate its algorithm and compare it with other competing algorithms.
Scene text detection and recognition: recent advances and future trends
TLDR
This literature review can serve as a good reference for researchers in the areas of scene text detection and recognition and identify state-of-the-art algorithms, and predict potential research directions in the future.
Reading Text in the Wild with Convolutional Neural Networks
TLDR
An end-to-end system for text spotting—localising and recognising text in natural scene images—and text based image retrieval and a real-world application to allow thousands of hours of news footage to be instantly searchable via a text query is demonstrated.
Symmetry-based text line detection in natural scenes
TLDR
This work investigates the problem of scene text detection from an alternative perspective and proposes a novel algorithm for it that exploits the symmetry property of character groups and allows for direct extraction of text lines from natural images.
FASText: Efficient Unconstrained Scene Text Detector
TLDR
A novel easy-to-implement stroke detector based on an efficient pixel intensity comparison to surrounding pixels that efficiently detected and text fragments are subsequently extracted by local thresholding guided by keypoint properties.
Real-time scene text localization and recognition
TLDR
The proposed end-to-end real-time scene text localization and recognition method achieves state-of-the-art text localization results amongst published methods and it is the first one to report results for end- to-end text recognition.
...
...