Image Binarization for End-to-End Text Understanding in Natural Images

@article{Milyaev2013ImageBF,
  title={Image Binarization for End-to-End Text Understanding in Natural Images},
  author={S. Milyaev and O. Barinova and Tatiana Novikova and P. Kohli and V. Lempitsky},
  journal={2013 12th International Conference on Document Analysis and Recognition},
  year={2013},
  pages={128-132}
}
While modern off-the-shelf OCR engines show particularly high accuracy on scanned text, text detection and recognition in natural images still remains a challenging problem. [...] Key Result Our main finding is thus the fact that image binarization methods combined with additional filtering of generated connected components and off-the-shelf OCR engines can achieve state-of-the-art performance for end-to-end text understanding in natural images.Expand
Fast and accurate scene text understanding with image binarization and off-the-shelf OCR
TLDR
Evaluation across different metrics on established natural image text recognition benchmarks shows that the simple and fast image binarization method combined with off-the-shelf OCR engine achieves state-of- the-art performance for end-to-end text understanding in natural images and outperforms recent fancy methods. Expand
Recognition and Retrieval in Natural Scene Images
In the past few years, text in natural scene images has gained potential to be a key feature for content based retrieval. They can be extracted and used in search engines, providing relevantExpand
Scene Text Recognition: No Country for Old Men?
TLDR
This paper confirms that a conventional shape-based OCR engine would be able to produce competitive results in the end-to-end scene text recognition task when provided with a conveniently preprocessed image. Expand
A novel binarization approach for text in images
TLDR
This paper presents an effective method to extract characters in images and video frames by assuming that background pixels possess good spatial connectivity and high appearance similarity to boundary pixels in a cropped text string image. Expand
Text detection and recognition in natural scenes and consumer videos
TLDR
The event detection system built upon the OCR output of this approach outperformed multiple other OCR-only based submissions in the recently concluded NIST TRECVID 2013 multimedia event detection evaluations. Expand
Unsupervised refinement of color and stroke features for text binarization
TLDR
This work uses a novel energy function to formulate the text binarization problem, and minimize the energy function with an iterative graph cut-based algorithm that is robust to variations in foreground and background as it learns Gaussian mixture models for color and strokes in each iteration of the graph cut. Expand
Exploiting Color Information for Better Scene Text Recognition
TLDR
A pipeline of image processing operations involving the bilateral regression for the identification of characters in the images and a pre-processing step has been proposed to increase the performance of bilateral regression based character identification. Expand
Text Detection in Natural Scene Images Leveraging Context Information
TLDR
This paper focuses on building a confidence map model by integrating the candidate appearance and the relationships with its adjacent candidates by leveraging context information for text detection in natural scene images. Expand
AN EMPIRICAL STUDY ON BINARIZATION OF NATURAL SCENE WORD IMAGES USING TRADITIONAL METHODS
TLDR
Four wellknown document based binarization algorithms have been tested for their suitability to natural scene word images and results shows that Otsu algorithm outperforms as compared to other three methods. Expand
Degraded Document Image Binarization using Novel Background Estimation Technique
Over the past few decades, the use of scanned historical document images has increased dramatically, especially with the emergence of online libraries and standard benchmark datasets like DIBCO. TheExpand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 30 REFERENCES
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. Expand
End-to-end text recognition with convolutional neural networks
TLDR
This paper combines the representational power of large, multilayer neural networks together with recent developments in unsupervised feature learning, which allows them to use a common framework to train highly-accurate text detector and character recognizer modules. Expand
An Objective Evaluation Methodology for Document Image Binarization Techniques
TLDR
An objective evaluation methodology that aims to reduce the human involvement in the ground truth construction and consecutive testing and a benchmarking of the six most promising state-of-the-art binarization algorithms based on the proposed methodology is presented. Expand
Adaptive document image binarization
TLDR
A new method is presented for adaptive document image binarization, where the page is considered as a collection of subcomponents such as text, background and picture, which adapts and performs well in each case qualitatively and quantitatively. Expand
Text detection from natural scene images: towards a system for visually impaired persons
TLDR
A system that reads the text encountered in natural scenes with the aim to provide assistance to the visually impaired persons and evaluates several character extraction methods based on connected components. Expand
An MRF Model for Binarization of Natural Scene Text
TLDR
This work represents the pixels in a document image as random variables in an MRF, and introduces a new energy function on these variables to find the optimal binarization, using an iterative graph cut scheme. Expand
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. Expand
A framework for the assessment of text extraction algorithms on complex colour images
TLDR
A complete framework for the evaluation of text extraction methods at multiple levels is described, a detailed ground-truth specification is provided and a case study is presented on how this framework can be used in a real-life situation. Expand
Binarization of low quality text using a Markov random field model
TLDR
A new technique based on a Markov random field model of the document and the model parameters (clique potentials) are learned from training data and the binary image is estimated in a Bayesian framework is introduced. Expand
Using Adaboost to Detect and Segment Characters from Natural Scenes
TLDR
A robust connected-component (CC) based method for automatic detection and segmentation of text in real-scene images and 12 novel features which are insensitive to noise, scale, text orientation and text language are proposed. Expand
...
1
2
3
...