EAST: An Efficient and Accurate Scene Text Detector

By Xinyu Zhou, Cong Yao, He Wen, Yuzhi Wang, Shuchang Zhou, Weiran He, Jiajun Liang. 2017

1,675 citations recorded by the source corpus.

Previous approaches for scene text detection have already achieved promising performances across various benchmarks. However, they usually fall short when dealing with challenging scenarios, even when equipped with deep neural network models, because the overall performance is determined by the interplay of multiple stages and components in the pipelines. In this work, we propose a simple yet powerful pipeline that yields fast and accurate text detection in natural scenes. 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 standard datasets including ICDAR 2015, COCO-Text and MSRA-TD500 demonstrate that the proposed algorithm significantly outperforms state-of-the-art methods in terms of both accuracy and efficiency. On the ICDAR 2015 dataset, the proposed algorithm achieves an F-score of 0.7820 at 13.2fps at 720p resolution.

Subfields: Computer Vision and Pattern Recognition, Media Technology

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

In Media Technology

Citations in the corpus

FCOS: Fully Convolutional One-Stage Object Detection (2019, methodology): “Beside, more signiﬁcantly, these methods are mainly used in special domain objection detection such as scene text detection [25] or face detection [24, 9], since it is believed that these methods do not work well when applied to generic object detection with highly overlapped bounding boxes.”
Scene Text Visual Question Answering (2019, background): “Several works have been proposed addressing text detection such as [32, 31, 55, 16] which are mostly comprised by a Fully Convolutional Neural Network.”
PIXOR: Real-time 3D Object Detection from Point Clouds (2018, methodology): “For single-class object detection, DenseBox [17] and EAST [38] show that single-stage detector also works well without using manually designed anchors.”
MMRotate: A Rotated Object Detection Benchmark using PyTorch (2022, methodology): “In light of this, deep learning has also been applied to areas such as faces detection [27], text detection [12, 13, 17, 20, 45] and aerial images detection [32, 35, 38].”
Rotation-Sensitive Regression for Oriented Scene Text Detection (2018, background): “The works in [11, 26] are such examples; 2) Multi-oriented text detectors [48, 50, 51, 38, 29, 13, 12, 14, 46] which focus on detecting text of arbitrary orientations.”
Rosetta: Large Scale System for Text Detection and Recognition in Images (2018, methodology): “Following Jaderberg’s work, many new methods have recently appeared that use CNN architectures to detect words in images, including [16, 21, 25, 32].”
Real-time Scene Text Detection with Differentiable Binarization (2019, methodology): “EAST (Zhou et al. 2017) and DeepReg (He et al.”
Look More Than Once: An Accurate Detector for Text of Arbitrary Shapes (2019, methodology): “Most of existing text detection methods [14, 15, 24, 42, 8] achieve good performance in a controlled environment where text instances have regular shapes and aspect ratios, e.”
Efficient and Accurate Arbitrary-Shaped Text Detection With Pixel Aggregation Network (2019, methodology): “EAST [57] and DeepReg [17] adopt FCNs to predict shrinkable text score maps and perform per-pixel regression, followed by a postprocessing NMS. TextSnake [35] models text instances with ordered disks and text center lines, which is able to represent text in arbitrary shapes.”
Character Region Awareness for Text Detection (2019, background): “Recently, scene text detectors based on deep learning have shown promising performance [8, 40, 21, 4, 11, 10, 12, 13, 17, 24, 25, 32, 26].”
Detecting Curve Text in the Wild: New Dataset and New Solution (2017, methodology): “Note that for East [38] and Seglink [27], we re-implement these methods based on the unofficial source codes from github, and for fair comparison, we do not use huge synthetic data to pre-train seglink which may reduce its performance.”
Dense Label Encoding for Boundary Discontinuity Free Rotation Detection (2020, methodology): “Many rotation detectors (including those for aerial image [46, 15, 47, 2, 6, 51, 45, 30, 48, 49, 50], scene text [56, 23, 14, 26, 19, 18] and face [34, 13, 33]) are derived based on the vanilla detection algorithms [10, 32, 31, 5, 20, 21].”
CORD: A Consolidated Receipt Dataset for Post-OCR Parsing (2019, methodology): “1 Introduction Optical character recognition (OCR) is a technique for converting images of characters into digitized texts [1, 2].”
Arbitrary-Oriented Object Detection with Circular Smooth Label (2020, background): “In particular, rotation detection has played a huge role in the field of aerial images [2, 4, 41, 42, 44], scene text [12, 18, 19, 24, 27, 49] and face [11, 33, 34].”
Object Detection in 20 Years: A Survey (2019, methodology): “The first group of methods frame the text detection as a special case of general object detection [251, 348–357].”
Mask TextSpotter: An End-to-End Trainable Neural Network for Spotting Text with Arbitrary Shapes (2018, background): “A large number of methods have been proposed to detect scene text [7, 36, 37, 50, 19, 23, 54, 21, 47, 54, 56, 30, 52, 55, 34, 15, 48, 43, 57, 16, 35, 31].”
FCOS: A Simple and Strong Anchor-Free Object Detector (2020, neutral): “Besides, more significantly, these methods are mainly used in special domain objection detection such as scene text detection [17], [18] or face detection [16], [19], since it is believed that these methods do not work well when applied to generic object detection with highly overlapped bounding box”
TextSnake: A Flexible Representation for Detecting Text of Arbitrary Shapes (2018, methodology): “Numerous innovative works [1,2,3,4,5,6,7,8,9,10,11] are proposed, achieving excellent performances on standard benchmarks.”