Scene Text Detection via Holistic, Multi-Channel Prediction

Abstract

Recently, scene text detection has become an active research topic in computer vision and document analysis, because of its great importance and significant challenge. However, vast majority of the existing methods detect text within local regions, typically through extracting character, word or line level candidates followed by candidate aggregation and false positive elimination, which potentially exclude the effect of wide-scope and long-range contextual cues in the scene. To take full advantage of the rich information available in the whole natural image, we propose to localize text in a holistic manner, by casting scene text detection as a semantic segmentation problem. The proposed algorithm directly runs on full images and produces global, pixel-wise prediction maps, in which detections are subsequently formed. To better make use of the properties of text, three types of information regarding text region, individual characters and their relationship are estimated, with a single Fully Convolutional Network (FCN) model. With such predictions of text properties, the proposed algorithm can simultaneously handle horizontal, multi-oriented and curved text in real-world natural images. The experiments on standard benchmarks, including ICDAR 2013, ICDAR 2015 and MSRA-TD500, demonstrate that the proposed algorithm substantially outperforms previous state-of-the-art approaches. Moreover, we report the first baseline result on the recently-released, large-scale dataset COCO-Text.

10 pages, 9 figures, 5 tables

References in corpus (8)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Caffe: Convolutional Architecture for Fast Feature Embedding
• Synthetic Data and Artificial Neural Networks for Natural Scene Text Recognition
• Robust Text Detection in Natural Scene Images
• Speeding up Convolutional Neural Networks with Low Rank Expansions
• Holistically-Nested Edge Detection
• COCO-Text: Dataset and Benchmark for Text Detection and Recognition in Natural Images
• Reading Text in the Wild with Convolutional Neural Networks

Cited by in corpus (49)

• A Survey of Deep Learning-based Object Detection
• TextBoxes++: A Single-Shot Oriented Scene Text Detector
• Object Detection in 20 Years: A Survey
• TextField: Learning A Deep Direction Field for Irregular Scene Text Detection
• EAST: An Efficient and Accurate Scene Text Detector
• Scene Text Detection and Recognition: The Deep Learning Era
• Efficient and Accurate Arbitrary-Shaped Text Detection with Pixel Aggregation Network
• Weak Supervision for Generating Pixel-Level Annotations in Scene Text Segmentation
• Selective Feature Connection Mechanism: Concatenating Multi-layer CNN Features with a Feature Selector
• Character Region Awareness for Text Detection
• Single Shot Text Detector with Regional Attention
• PixelLink: Detecting Scene Text via Instance Segmentation
• Mask TextSpotter: An End-to-End Trainable Neural Network for Spotting Text with Arbitrary Shapes
• WordSup: Exploiting Word Annotations for Character based Text Detection
• Multi-Oriented Scene Text Detection via Corner Localization and Region Segmentation
• IncepText: A New Inception-Text Module with Deformable PSROI Pooling for Multi-Oriented Scene Text Detection
• 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
• Learning Markov Clustering Networks for Scene Text Detection
• Text Detection and Recognition in the Wild: A Review
• A Survey of Deep Learning Approaches for OCR and Document Understanding
• Fourier Contour Embedding for Arbitrary-Shaped Text Detection
• End-to-End Subtitle Detection and Recognition for Videos in East Asian Languages via CNN Ensemble with Near-Human-Level Performance
• A pooling based scene text proposal technique for scene text reading in the wild
• Scene Text Detection with Supervised Pyramid Context Network
• Detecting Oriented Text in Natural Images by Linking Segments
• 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
• Towards End-to-End Text Spotting in Natural Scenes
• PuzzleNet: Scene Text Detection by Segment Context Graph Learning
• ArbiText: Arbitrary-Oriented Text Detection in Unconstrained Scene
• DeRPN: Taking a further step toward more general object detection
• RRPN++: Guidance Towards More Accurate Scene Text Detection
• A Single Shot Text Detector with Scale-adaptive Anchors
• A New Unified Method for Detecting Text from Marathon Runners and Sports Players in Video
• TextRay: Contour-based Geometric Modeling for Arbitrary-shaped Scene Text Detection
• Cascaded Segmentation-Detection Networks for Word-Level Text Spotting
• Learning Robust Feature Representations for Scene Text Detection
• Location-Aware Feature Selection Text Detection Network
• Correlation Propagation Networks for Scene Text Detection
• Scene Text Detection with Selected Anchor
• MT: Multi-Perspective Feature Learning Network for Scene Text Detection
• RFBTD: RFB Text Detector
• Conceptual Text Region Network: Cognition-Inspired Accurate Scene Text Detection
• A method for detecting text of arbitrary shapes in natural scenes that improves text spotting
• All you need is a second look: Towards Tighter Arbitrary shape text detection
• Accurate Scene Text Detection through Border Semantics Awareness and Bootstrapping
• TextContourNet: a Flexible and Effective Framework for Improving Scene Text Detection Architecture with a Multi-task Cascade