Text Flow: A Unified Text Detection System in Natural Scene Images

@article{Tian2015TextFA,
  title={Text Flow: A Unified Text Detection System in Natural Scene Images},
  author={Shangxuan Tian and Yifeng Pan and Chang Huang and Shijian Lu and Kai Yu and Chew Lim Tan},
  journal={2015 IEEE International Conference on Computer Vision (ICCV)},
  year={2015},
  pages={4651-4659}
}
The prevalent scene text detection approach follows four sequential steps comprising character candidate detection, false character candidate removal, text line extraction, and text line verification. [] Key Method With character candidates detected by cascade boosting, the min-cost flow network model integrates the last three sequential steps into a single process which solves the error accumulation problem at both character level and text line level effectively. The proposed technique has been tested on…

Figures and Tables from this paper

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.
Feature Fusion Network for Scene Text Detection
TLDR
This model enables an end-to-end scene text detector which can detect text regions of various scales without a pre-trained model and achieves state-of-the-art results on ICDAR 2013 and COCO-Text benchmarks.
Text Detection in Natural Scene Images with Text Line Construction
  • Zihao Liu, Qiwei Shen, Chun Wang
  • Computer Science
    2018 IEEE International Conference on Information Communication and Signal Processing (ICICSP)
  • 2018
TLDR
A new text region recognition algorithm that can accurately localize image text regions in natural image with complex background based on the anchor mechanism of the faster R-CNN, taking into account the special features of the text area relative to other object detect tasks.
Scene Text Detection with Text Statistical Characteristics and Deep Neural Network
TLDR
The experimental results show that the proposed Text-SSD method achieved the state-of-the-art performance on the benchmark dataset ICDAR2013 in the detection accuracy and achieves the fastest speed compared with several latest text detection method based on deep neural network.
A Character Flow Framework for Multi-Oriented Scene Text Detection
TLDR
A novel multi-oriented scene text detection framework, which includes two main modules: character instance segmentation and character flow construction, and a joint network of FPN and bidirectional long shortterm memory is developed to explore the context information among isolated characters, which are finally grouped into character flows.
Max-Pooling Based Scene Text Proposal for Scene Text Detection
TLDR
A max-pooling based scene text proposal technique aiming for automatic extraction of texts in scenes that obtains superior proposal performance as compared with state-of-the-arts, especially when a small number of proposals is selected.
Aggregating Local Context for Accurate Scene Text Detection
TLDR
A novel Convolutional Neural Network architecture is designed that aggregates local surrounding information for cascaded, fast and accurate detection of scene text regions and a novel grouping algorithm on top of detected character graph.
Natural Scene Text Detection Based on Deep Supervised Fully Convolutional Network
TLDR
Experimental results on the ICDAR 2015 datasets and MSRA-TD500 datasets have proven that the proposed method outperforms the state-of-the-art methods by a noticeable margin on F-score.
...
...

References

SHOWING 1-10 OF 37 REFERENCES
A Hybrid Approach to Detect and Localize Texts in Natural Scene Images
TLDR
A hybrid approach to robustly detect and localize texts in natural scene images using a text region detector, a conditional random field model, and a learning-based energy minimization method are presented.
Robust Text Detection in Natural Scene Images
TLDR
An accurate and robust method for detecting texts in natural scene images using a fast and effective pruning algorithm to extract Maximally Stable Extremal Regions (MSERs) as character candidates using the strategy of minimizing regularized variations is proposed.
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.
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.
Scene text extraction based on edges and support vector regression
TLDR
This paper presents a scene text extraction technique that automatically detects and segments texts from scene images using a support vector regression model that is trained using bags-of-words representation.
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.
Scene text detection using graph model built upon maximally stable extremal regions
End-to-end scene text recognition
TLDR
While scene text recognition has generally been treated with highly domain-specific methods, the results demonstrate the suitability of applying generic computer vision methods.
A Unified Framework for Multioriented Text Detection and Recognition
  • C. Yao, X. Bai, Wenyu Liu
  • Computer Science
    IEEE Transactions on Image Processing
  • 2014
TLDR
A unified framework for text detection and recognition in natural images using exactly the same features and classification scheme and a new dictionary search method is proposed, to correct the recognition errors usually caused by confusions among similar yet different characters.
Deep Features for Text Spotting
TLDR
A Convolutional Neural Network classifier is developed that can be used for text spotting in natural images and a method of automated data mining of Flickr, that generates word and character level annotations is used to form an end-to-end, state-of-the-art text spotting system.
...
...