EAST: An Efficient and Accurate Scene Text Detector

Abstract

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.

Accepted to CVPR 2017, fix equation (3)

References in corpus (5)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Fully Convolutional Networks for Semantic Segmentation
• UnitBox: An Advanced Object Detection Network
• Scene Text Detection via Holistic, Multi-Channel Prediction
• PVANET: Deep but Lightweight Neural Networks for Real-time Object Detection

Cited by in corpus (29)

• R2CNN: Rotational Region CNN for Orientation Robust Scene Text Detection
• MMRotate: A Rotated Object Detection Benchmark using PyTorch
• Rosetta: Large scale system for text detection and recognition in images
• COVID-19 Literature Knowledge Graph Construction and Drug Repurposing Report Generation
• Efficient and Accurate Arbitrary-Shaped Text Detection with Pixel Aggregation Network
• Selective Feature Connection Mechanism: Concatenating Multi-layer CNN Features with a Feature Selector
• PixelLink: Detecting Scene Text via Instance Segmentation
• WordSup: Exploiting Word Annotations for Character based Text Detection
• IncepText: A New Inception-Text Module with Deformable PSROI Pooling for Multi-Oriented Scene Text Detection
• Sliding Line Point Regression for Shape Robust Scene Text Detection
• Feature Enhancement Network: A Refined Scene Text Detector
• TRIE: End-to-End Text Reading and Information Extraction for Document Understanding
• UTRNet: High-Resolution Urdu Text Recognition In Printed Documents
• Geometry Normalization Networks for Accurate Scene Text Detection
• Verisimilar Image Synthesis for Accurate Detection and Recognition of Texts in Scenes
• A Survey on Deep Domain Adaptation and Tiny Object Detection Challenges, Techniques and Datasets
• FOTS: Fast Oriented Text Spotting with a Unified Network
• You Only Recognize Once: Towards Fast Video Text Spotting
• ArbiText: Arbitrary-Oriented Text Detection in Unconstrained Scene
• Mask is All You Need: Rethinking Mask R-CNN for Dense and Arbitrary-Shaped Scene Text Detection
• Text Perceptron: Towards End-to-End Arbitrary-Shaped Text Spotting
• Detecting Text in the Wild with Deep Character Embedding Network
• STELA: A Real-Time Scene Text Detector with Learned Anchor
• AE TextSpotter: Learning Visual and Linguistic Representation for Ambiguous Text Spotting
• Scene Text Detection with Selected Anchor
• Correlation Propagation Networks for Scene Text Detection
• Deep Learning Based Vehicle Tracking System Using License Plate Detection And Recognition
• Distantly Supervised Semantic Text Detection and Recognition for Broadcast Sports Videos Understanding
• Challenging Images For Minds and Machines