An MRF Model for Binarization of Natural Scene Text
Published 1 September 2011Open access
Anand Mishra, Karteek Alahari, C. V. Jawahar
Citations109
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
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.
Abstract
International audience
Keywords
Computer Science
IEEE Transactions on Pattern Analysis and Machine IntelligenceAn experimental comparison of min-cut/max- flow algorithms for energy minimization in vision
4,600 Citations2004Yuri Boykov, Vladimir Kolmogorov
Interactive graph cuts for optimal boundary & region segmentation of objects in N-D images
3,676 Citations2002Yuri Boykov, Marie‐Pierre Jolly
A new technique for general purpose interactive segmentation of N-dimensional images where the user marks certain pixels as "object" or "background" to provide hard constraints for segmentation.
IEEE Transactions on Pattern Analysis and Machine IntelligenceWhat energy functions can be minimized via graph cuts?
3,147 Citations2004Vladimir Kolmogorov, Ramin Zabih
Pattern RecognitionAdaptive document image binarization
2,249 Citations2000J. Sauvola, Matti Pietikäinen
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.
Lecture notes in computer scienceInteractive Image Segmentation Using an Adaptive GMMRF Model
526 Citations2004Andrew Blake, Carsten Rother +3 more
Estimation is performed by solving a graph cut problem for which very efficient algorithms have recently been developed, however the model depends on parameters which must be set by hand and the aim of this work is for those constants to be learned from image data.
ICDAR 2009 Document Image Binarization Contest (DIBCO 2009)
294 Citations2009Basilis Gatos, Konstantinos Ntirogiannis +1 more
Computer Vision Graphics and Image ProcessingThreshold selection based on a simple image statistic
252 Citations1985Josef Kittler, J. Illingworth +1 more
A novel method based on image statistics which can be computed without histogramming the grey level values of the image is proposed, which is shown to be effective on a number of practical examples.
Zenodo (CERN European Organization for Nuclear Research)An Evaluation Technique for Binarization Algorithms
79 Citations2008Pyrrhos Stathis, Ergina Kavallieratou +1 more
This paper proposes a new technique for the validation of document binarization algorithms that is simple in its implementation and can be performed on anybinarization algorithm since it doesn't require anything more than the binarized stage.
Binarization of low quality text using a Markov random field model
67 Citations2003Christian Wolf, David Doermann
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.
Binarization of Color Characters in Scene Images Using k-means Clustering and Support Vector Machines
45 Citations2010Kohei Kita, Toru Wakahara
A new technique for binalizing multicolored characters subject to heavy degradations by selection of a single binarized image with the maximum degree of “character likeness” as an optimal binarization result.
Feature Based Binarization of Document Images Degraded by Uneven Light Condition
32 Citations2009Jung Gap Kuk, Nam Ik Cho
Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIEColor binarization for complex camera-based images
26 Citations2005Cline Thillou, Bernard Gosselin
A new automatic color thresholding based on wavelet denoising and color clustering with K-means is described in order to segment text information in a camera-based image to conclude that the use of a discrimination between kinds of backgrounds gives better results in terms of Precision and Recall.
Markov random field based binarization for hand-held devices captured document images
16 Citations2010Xujun Peng, Srirangaraj Setlur +2 more
A novel Markov random fields based binarization algorithm is proposed to segment foreground text from document images captured using hand-held devices (such as cell-phone or digital camera) and outperforms other state-of-the-art approaches.