FASText: Efficient Unconstrained Scene Text Detector

@article{Busta2015FASTextEU,
  title={FASText: Efficient Unconstrained Scene Text Detector},
  author={Michal Busta and Luk{\'a}s Neumann and Jiri Matas},
  journal={2015 IEEE International Conference on Computer Vision (ICCV)},
  year={2015},
  pages={1206-1214}
}
We propose a novel easy-to-implement stroke detector based on an efficient pixel intensity comparison to surrounding pixels. [] Key Result When the proposed detector is plugged into a scene text localization and recognition pipeline, a state-of-the-art text localization accuracy is maintained whilst the processing time is significantly reduced.
Multi-oriented Scene Text Detection via Corner Localization and Region Segmentation
TLDR
This paper proposes to detect scene text by localizing corner points of text bounding boxes and segmenting text regions in relative positions and achieves better or comparable results in both accuracy and efficiency.
A Fast Uyghur Text Detector for Complex Background Images
TLDR
A FASTroke keypoint extractor, which is fast and stroke-specific, and can achieve the best performance on the UICBI-500 benchmark dataset.
Natural Scene Text Detection Based on Multi-Channel FASText
TLDR
Experimental result shows that the proposed multi-channel FASText based text detection method for natural scene images is effective to natural scene text detection.
Method for unconstrained text detection in natural scene image
TLDR
The authors present a simple and effective text detection method in natural scene image which is general for detecting scene text lines in different languages and achieves 82.94 and 75% F -measure.
Real-Time Text Localization in Natural Scene Images Using a Linear Spatial Filter
  • X. Gironés, Carme Julià
  • Computer Science
    2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR)
  • 2017
TLDR
The main contribution of the proposed method is its execution speed, being capable of processing 1080p HD video at nearly 30 frames per second on a standard laptop, and it delivers competitive results interms of precision and recall on the ICDAR 2013 Robust Reading dataset.
TextBoxes++: A Single-Shot Oriented Scene Text Detector
TLDR
An end- to-end trainable fast scene text detector, named TextBoxes++, which detects arbitrary-oriented scene text with both high accuracy and efficiency in a single network forward pass, and significantly outperforms the state-of-the-art approaches for word spotting and end-to-end text recognition tasks on popular benchmarks.
Vesselness for text detection in historical document images
TLDR
A new method to detect text in images, particularly in historical document images is described, using the use of the vesselness filter as a new preprocessing step for text detection.
Fast Scene Text Detection with RT-LoG Operator and CNN
TLDR
The keypoint grouping method is proposed by first applying the real-time Laplacian of Gaussian operator (RT-LoG) to detect keypoints, which will be grouped to produce the character patterns.
EAST: An Efficient and Accurate Scene Text Detector
TLDR
This work proposes a simple yet powerful pipeline that yields fast and accurate text detection in natural scenes, and significantly outperforms state-of-the-art methods in terms of both accuracy and efficiency.
Morphology-based hierarchical representation with application to text segmentation in natural images
TLDR
A hierarchical image representation, based on the morphological Laplace operator, is proposed, which is used to give a robust text segmentation, and can be applied to document binarization, with the interesting feature of getting also reverse-video text.
...
...

References

SHOWING 1-10 OF 38 REFERENCES
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 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.
On Combining Multiple Segmentations in Scene Text Recognition
TLDR
An end-to-end real-time scene text localization and recognition method that achieves state-of-the-art text localization results on the ICDAR 2011 Robust Reading dataset and shows that, despite using theoretically scale-invariant methods, operating on a coarse Gaussian scale space pyramid yields improved results as many typographical artifacts are eliminated.
Strokelets: A Learned Multi-scale Representation for Scene Text Recognition
  • C. Yao, X. Bai, Baoguang Shi, Wenyu Liu
  • Computer Science
    2014 IEEE Conference on Computer Vision and Pattern Recognition
  • 2014
TLDR
This paper proposes a novel multi-scale representation for scene text recognition that consists of a set of detectable primitives, termed as strokelets, which capture the essential substructures of characters at different granularities.
Text Localization Based on Fast Feature Pyramids and Multi-Resolution Maximally Stable Extremal Regions
TLDR
This work proposes a novel hybrid text localization approach that exploits Multi-resolution Maximally Stable Extremal Regions to discard false-positive detections from the text confidence maps generated by a Fast Feature Pyramid based sliding window classifier.
Region-Based Discriminative Feature Pooling for Scene Text Recognition
TLDR
This work proposes a discriminative feature pooling method that automatically learns the most informative sub-regions of each scene character within a multi-class classification framework, whereas each sub-region seamlessly integrates a set of low-level image features through integral images.
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 detection using graph model built upon maximally stable extremal regions
Detecting text in natural scenes with stroke width transform
TLDR
A novel image operator is presented that seeks to find the value of stroke width for each image pixel, and its use on the task of text detection in natural images is demonstrated.
Orientation Robust Text Line Detection in Natural Images
TLDR
This paper treats text line detection as a graph partitioning problem, where each vertex is represented by a Maximally Stable Extremal Region (MSER), and uses higher-order correlation clustering to partition the MSERs into text line candidates.
...
...