TextBoxes: A Fast Text Detector with a Single Deep Neural Network

Abstract

This paper presents an end-to-end trainable fast scene text detector, named TextBoxes, which detects scene text with both high accuracy and efficiency in a single network forward pass, involving no post-process except for a standard non-maximum suppression. TextBoxes outperforms competing methods in terms of text localization accuracy and is much faster, taking only 0.09s per image in a fast implementation. Furthermore, combined with a text recognizer, TextBoxes significantly outperforms state-of-the-art approaches on word spotting and end-to-end text recognition tasks.

Accepted by AAAI2017

References in corpus (7)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Synthetic Data for Text Localisation in Natural Images
• DeepText: A Unified Framework for Text Proposal Generation and Text Detection in Natural Images
• End-to-End Text Recognition with Hybrid HMM Maxout Models
• Multi-Oriented Text Detection with Fully Convolutional Networks
• An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition
• TextProposals: a Text-specific Selective Search Algorithm for Word Spotting in the Wild

Cited by in corpus (109)

• A Survey of Deep Learning-based Object Detection
• TextBoxes++: A Single-Shot Oriented Scene Text Detector
• Object Detection in 20 Years: A Survey
• R2CNN: Rotational Region CNN for Orientation Robust Scene Text Detection
• TextField: Learning A Deep Direction Field for Irregular Scene Text Detection
• R3Det: Refined Single-Stage Detector with Feature Refinement for Rotating Object
• Scene Text Detection and Recognition: The Deep Learning Era
• A Single-Shot Arbitrarily-Shaped Text Detector based on Context Attended Multi-Task Learning
• Efficient and Accurate Arbitrary-Shaped Text Detection with Pixel Aggregation Network
• Learning Modulated Loss for Rotated Object Detection
• Single Shot Text Detector with Regional Attention
• Character Region Awareness for Text Detection
• Pyramid Mask Text Detector
• PixelLink: Detecting Scene Text via Instance Segmentation
• Real-time Scene Text Detection with Differentiable Binarization
• Text Recognition in the Wild: A Survey
• Mask TextSpotter: An End-to-End Trainable Neural Network for Spotting Text with Arbitrary Shapes
• Detecting Multi-Oriented Text with Corner-based Region Proposals
• Multi-Oriented Scene Text Detection via Corner Localization and Region Segmentation
• Shape Robust Text Detection with Progressive Scale Expansion Network
• ABCNet: Real-time Scene Text Spotting with Adaptive Bezier-Curve Network
• Beyond Visual Semantics: Exploring the Role of Scene Text in Image Understanding
• Scene Text Recognition from Two-Dimensional Perspective
• Stroke-Based Scene Text Erasing Using Synthetic Data for Training
• Scene Text Synthesis for Efficient and Effective Deep Network Training
• TextSnake: A Flexible Representation for Detecting Text of Arbitrary Shapes
• An end-to-end TextSpotter with Explicit Alignment and Attention
• Towards End-to-end Text Spotting with Convolutional Recurrent Neural Networks
• Learning Markov Clustering Networks for Scene Text Detection
• Pixel-Anchor: A Fast Oriented Scene Text Detector with Combined Networks
• Sliding Line Point Regression for Shape Robust Scene Text Detection
• Text Detection and Recognition in the Wild: A Review
• A Survey of Deep Learning Approaches for OCR and Document Understanding
• Fused Text Segmentation Networks for Multi-oriented Scene Text Detection
• PAN++: Towards Efficient and Accurate End-to-End Spotting of Arbitrarily-Shaped Text
• Towards Unconstrained End-to-End Text Spotting
• A pooling based scene text proposal technique for scene text reading in the wild
• ContourNet: Taking a Further Step toward Accurate Arbitrary-shaped Scene Text Detection
• Scene Text Detection with Supervised Pyramid Context Network
• SEED: Semantics Enhanced Encoder-Decoder Framework for Scene Text Recognition
• ABCNet v2: Adaptive Bezier-Curve Network for Real-time End-to-end Text Spotting
• Rotation-Sensitive Regression for Oriented Scene Text Detection
• Look More Than Once: An Accurate Detector for Text of Arbitrary Shapes
• TextMountain: Accurate Scene Text Detection via Instance Segmentation
• Feature Enhancement Network: A Refined Scene Text Detector
• Transfer Learning for Scene Text Recognition in Indian Languages
• CentripetalText: An Efficient Text Instance Representation for Scene Text Detection
• Arbitrary-Shaped Text Detection withAdaptive Text Region Representation
• Arbitrary Shape Scene Text Detection with Adaptive Text Region Representation
• ICDAR 2019 Competition on Large-scale Street View Text with Partial Labeling -- RRC-LSVT
• TRIE: End-to-End Text Reading and Information Extraction for Document Understanding
• Verisimilar Image Synthesis for Accurate Detection and Recognition of Texts in Scenes
• Geometry Normalization Networks for Accurate Scene Text Detection
• ScanSSD: Scanning Single Shot Detector for Mathematical Formulas in PDF Document Images
• A Survey on Deep Domain Adaptation and Tiny Object Detection Challenges, Techniques and Datasets
• Mask R-CNN with Pyramid Attention Network for Scene Text Detection
• Convolutional Character Networks
• PolarMask++: Enhanced Polar Representation for Single-Shot Instance Segmentation and Beyond
• Mask TextSpotter v3: Segmentation Proposal Network for Robust Scene Text Spotting
• FAST: Faster Arbitrarily-Shaped Text Detector with Minimalist Kernel Representation
• Towards End-to-End Text Spotting in Natural Scenes
• Deep Scene Text Detection with Connected Component Proposals
• SynthText3D: Synthesizing Scene Text Images from 3D Virtual Worlds
• What If We Only Use Real Datasets for Scene Text Recognition? Toward Scene Text Recognition With Fewer Labels
• PuzzleNet: Scene Text Detection by Segment Context Graph Learning
• Don't only Feel Read: Using Scene text to understand advertisements
• GA-DAN: Geometry-Aware Domain Adaptation Network for Scene Text Detection and Recognition
• DeRPN: Taking a further step toward more general object detection
• All You Need Is Boundary: Toward Arbitrary-Shaped Text Spotting
• TextCohesion: Detecting Text for Arbitrary Shapes
• ShopSign: a Diverse Scene Text Dataset of Chinese Shop Signs in Street Views
• Self-Training for Domain Adaptive Scene Text Detection
• MOST: A Multi-Oriented Scene Text Detector with Localization Refinement
• Weakly-Supervised Arbitrary-Shaped Text Detection with Expectation-Maximization Algorithm
• Synthetic-to-Real Unsupervised Domain Adaptation for Scene Text Detection in the Wild
• RRPN++: Guidance Towards More Accurate Scene Text Detection
• ReLaText: Exploiting Visual Relationships for Arbitrary-Shaped Scene Text Detection with Graph Convolutional Networks
• Text Perceptron: Towards End-to-End Arbitrary-Shaped Text Spotting
• Exploring the Capacity of an Orderless Box Discretization Network for Multi-orientation Scene Text Detection
• TextNet: Irregular Text Reading from Images with an End-to-End Trainable Network
• Arbitrarily Shaped Scene Text Detection: A Decade of Advances and Systematic Analysis
• DocStruct: A Multimodal Method to Extract Hierarchy Structure in Document for General Form Understanding
• Location-Aware Feature Selection Text Detection Network
• TextTubes for Detecting Curved Text in the Wild
• Detecting Text in the Wild with Deep Character Embedding Network
• Soft-PHOC Descriptor for End-to-End Word Spotting in Egocentric Scene Images
• RSCA: Real-time Segmentation-based Context-Aware Scene Text Detection
• Integrating Scene Text and Visual Appearance for Fine-Grained Image Classification
• Learning Robust Feature Representations for Scene Text Detection
• A Feasible Framework for Arbitrary-Shaped Scene Text Recognition
• Scene Text Detection with Selected Anchor
• Deep Neural Network for Fast and Accurate Single Image Super-Resolution via Channel-Attention-based Fusion of Orientation-aware Features
• AE TextSpotter: Learning Visual and Linguistic Representation for Ambiguous Text Spotting
• Financial ticket intelligent recognition system based on deep learning
• Single Shot Scene Text Retrieval
• Correlation Propagation Networks for Scene Text Detection
• Predictive Ensemble Learning with Application to Scene Text Detection
• Semi-Bagging Based Deep Neural Architecture to Extract Text from High Entropy Images
• Research on All-content Text Recognition Method for Financial Ticket Image
• A method for detecting text of arbitrary shapes in natural scenes that improves text spotting
• A Multi-oriented Chinese Keyword Spotter Guided by Text Line Detection
• SocialML: machine learning for social media video creators
• Attention-based Feature Decomposition-Reconstruction Network for Scene Text Detection
• Towards Pure End-to-End Learning for Recognizing Multiple Text Sequences from an Image
• Conceptual Text Region Network: Cognition-Inspired Accurate Scene Text Detection
• All You Need is a Second Look: Towards Arbitrary-Shaped Text Detection
• Accurate Scene Text Detection through Border Semantics Awareness and Bootstrapping
• Bidirectional Regression for Arbitrary-Shaped Text Detection
• Scene Text recognition with Full Normalization