An MRF Model for Binarization of Natural Scene Text
Summary (1 min read)
Summary
- Over the past two decades, numerous scientific studies have demonstrated that endocrine disrupting 70 chemicals (EDCs) elicit adverse effects on sensitive aquatic species, such as fish [1-7].
- The REP, in turn, is the ratio of the effect 222 concentration of the reference compound estradiol EC50(E2) and the chemical i’s EC50(i) (Equation 2).
- This result is supported by two recent reviews on the performance of current analytical 306 methods that have shown that 35 % of reviewed methods complied with the EQS for E2, while only one 307 method complied with the EQS for EE2 [49, 50].
- The situation for MELN is markedly different from that of ER-CALUX.
- 376 Thus, EEQchem results for MELN are strongly based on E1 concentrations – a compound that was always 377 measured (except for a few samples by Lab 2, Figure 3).
Did you find this useful? Give us your feedback
Citations
233 citations
Cites methods from "An MRF Model for Binarization of Na..."
...Datsets ICDAR03 (Full) ICDAR03 (50) ICDAR11 (Full) ICDAR11 (50) SVT MRF [5] 0.67 0.69 - - - IR [7] 0.75 0.77 - - - NESP [6] 0.66 - 0.73 - PLEX [16] 0.62 0.76 - - 0.57 HOG + CRF [10] - 0.82 - - 0.73 PBS [9] 0.79 0.87 0.83 0.87 0.74 WFST [11] 0.83 - 0.56 - 0.73 CNN [14] 0.84 0.90 - - 0.70 Proposed 0.82 0.92 0.83 0.91 0.83 ICDAR03(FULL) and ICDAR11(FULL) in Table 1), as well as with lexicon consisting of 50 random words from the test set (as denoted by ICDAR03(50) and ICDAR11(50) in Table 1)....
[...]
...Several systems have been reported that exploit Markov Random Field [5], Nonlinear color enhancement [6] and Inverse Rendering [7] to extract the character regions....
[...]
...The text segmentation methods (MRF, IR, and NESP) produce lower recognition accuracy than other methods because robust and accurate scene text segmentation by itself is an very challenging task....
[...]
...We compare our proposed method with eight state-of-the-art techniques, including markov random field method (MRF) [5], inverse rendering method (IR) [7], nonlinear color enhancement method (NESP) [6], pictorial structure method (PLEX) [16], HOG based conditional random field method (HOG+CRF) [10], weighted finite-state transducers method (WFST) [11], part based tree structure method (PBS) [9] and convolutional neural network method (CNN) [14]....
[...]
185 citations
Cites background from "An MRF Model for Binarization of Na..."
...A number of projects have explored the use of Markov random fields (MRF) for binarization [12, 18, 15, 11]....
[...]
155 citations
Cites background from "An MRF Model for Binarization of Na..."
...Variousmethods have been proposed to tackle these sub-problems, which includes text binariza- tion (Zhiwei et al. 2010; Mishra et al. 2011; Wakahara and Kita 2011; Lee and Kim 2013), text line segmentation (Ye et al. 2003), character segmentation (Nomura et al. 2005; Shivakumara et al. 2011; Roy et…...
[...]
...s for classification. Another discomposed the recognition process into a series of sub-problems. Various methods have been proposed to tackle these sub-problems, which includes text binarization [78], [105], [153], [182], text line segmentation [169], character segmentation [113], [126], [139], single JOURNAL OF LATEX CLASS FILES, VOL. X, NO. X, X X 3 Images Stroke Width Map Width Variance Map MSER Comp...
[...]
130 citations
Cites background from "An MRF Model for Binarization of Na..."
...When applied for texts in scene images, the recognition performance of these existing OCR systems is often not satisfactory because such texts could appear in arbitrary size, color, fonts, orientations, lighting, and background as illustrated in Fig....
[...]
129 citations
Cites methods from "An MRF Model for Binarization of Na..."
...Text segmentation methods (MRF [3], IR [5], and NESP [4]) produce lower recognition accuracy than other methods because robust and accurate scene text segmentation is a very challenging task....
[...]
...The compared techniques can be grouped into three categories including 1) Segmentation based techniques (markov random field method (MRF) [3], inverse rendering method (IR) [5], nonlinear color enhancement method (NESP) [4]) that segment the text regions from the word images, 2) Character level recognition techniques (HMM Maxout model (HMM) [9], HOG based conditional random field method (HOGCRF) [12], CNN model (CNN) [11], Part Based Tree structure method (PBS) [14] 1, Clustering sub-patches of characters method (Strokelets) [15], PhotoOCR [10] and Deep CNN Model (DCNN) [16]) that recognize word images through segmentation and integration of character recognition results and 3) Word level recognition techniques (Embedded attributes (AE) [18], Dynamic time warping (DTW) [17], and Whole Word Deep CNN Model(WWDCNN) [19]) that treat each word images as a whole without character segmentation....
[...]
...The compared techniques can be grouped into three categories including 1) Segmentation based techniques (markov random field method (MRF) [3], inverse rendering method (IR) [5], nonlinear color enhancement method (NESP) [4]) that segment the text regions from the word images, 2) Character level recognition techniques (HMM Maxout model (HMM) [9], HOG based conditional random field method (HOGCRF) [12], CNN model (CNN) [11], Part Based Tree structure method (PBS) [14] (1), Clustering sub-patches of characters method (Strokelets) [15], PhotoOCR [10] and Deep CNN Model (DCNN) [16]) that recognize word images through segmentation and integration of character recognition results and 3) Word level recognition techniques (Embedded attributes (AE) [18], Dynamic time warping (DTW) [17], and Whole Word Deep CNN Model(WWDCNN) [19]) that treat each word images as a whole without character segmentation....
[...]
References
37,017 citations
"An MRF Model for Binarization of Na..." refers methods in this paper
...We also compare our method with Otsu followed by colour thresholding (CT) [14]....
[...]
...Otsu followed by colour thresholding binarization proposed in [14] improves the word recognition accuracy but not significantly....
[...]
...Traditional thresholding based binarization can be categorized into two categories: the one which uses global threshold for the given document (like Otsu [5], Kittler et al. [6]) and the one with local thresholds (like Sauvola [7], Niblack [8])....
[...]
...To evaluate the performance of proposed binarization algorithm, we compare it with the well-known thresholding based binarization techniques like Otsu [5], Sauvola [7], Niblack [8], Kittler et al. [6]....
[...]
...Since this dataset consists of images of tight word boundaries, global methods (like [5], [6]) performs better than popular local methods....
[...]
5,670 citations
4,463 citations
3,571 citations
3,099 citations
"An MRF Model for Binarization of Na..." refers background or methods in this paper
...But these methods lack a principled formulation of the binarization problem of complex colour documents, and hence can not be generalized....
[...]
...Then, based on the data and smoothness terms in Equation (5) and (6) respectively, the graph is formed....
[...]
...All the implementations of the proposed method are done using C++ graph cut code [15] and Matlab....
[...]
Related Papers (5)
Frequently Asked Questions (12)
Q2. What is the way to make the binarization process more efficient?
iterative graph cut based binarization is also more suitable for their application as it refines seeds and, binarization output at each iteration and thus produces a clean binarization result even in case of noisy foreground/background distributions.
Q3. What is the energy function in Equation (1)?
Due to the introduction of GMMS the energy function in Equation (1) now becomes:E(x, k, θ, z) = Ei(x, k, θ, z) + Eij(x, z), (4)i.e. the data term depends on its assignment to GMM component.
Q4. How long does it take to produce a binary image?
The proposed method takes 32 seconds on average to produce final binary result for an image on system with 2 GB RAM and Intel R© CoreTM 2 Duo CPU with 2.93 GHz processor system.
Q5. What is the meaning of edginess difference?
(Note that by edginess difference term the authors mean, energy function with gradient magnitude difference in addition to difference in RGB colour space).
Q6. What is the common term used in the literature?
the smoothness term most commonly used in literature is the Potts model:Eij(x, z) = λ ∑(i,j)∈N exp−(zi − zj)2 2β2 [xi = xj ] dist(i, j) ,where λ determines the degree of smoothness, dist(i, j) is the Euclidean distance between neighbouring pixels i and j.
Q7. What is the gradient orientation of the edge pixel?
For every such edge pixel p the authors traverse the edge image in direction of θ until the authors hit an edge pixel q whose gradient orientation is (π−θ)± π36 (i.e. approximately opposite gradient direction).
Q8. how to make the energy function robust to low contrast colour images?
(5)In order to make the energy function robust to low contrast colour images the authors modify the smoothness term of the energy function by adding a new term which measures the “edginess” of the pixels as follows:Eij(x, z) = λ1 ∑(i,j)∈N [xi = xj ]exp(−β||zi − zj||2)+λ2 ∑(i,j)∈N [xi = xj ]exp(−β||wi − wj ||2).
Q9. What is the way to get the pixel colour from a GMMRF?
ITERATIVE GRAPH CUT BASED BINARIZATIONIn GMMRF framework [4], each pixel colour is generated from one of the 2c Gaussian Mixture Models (GMMS) (c GMMS for foreground and background each) with mean μ and covariance Σ i.e. each foreground colour pixel is generated from following distribution:p(zi|xi, θ, ki) = N (z, θ; μ(xi, ki), Σ(xi, ki)), (3) where N denotes a Gaussian distribution, xi ∈ {0, 1} and ki ∈ {1, ..., c}.
Q10. What are the main problems of the previous binarization algorithms?
Although most of these previous algorithms perform satisfactorily for many cases, they suffer from the problems like: (1) Manual tuning of parameters, (2) High sensitivity to the choice of parameters, (3) Handling images with uneven lighting, noisy background, similar foreground-background colours.
Q11. How do the authors determine the background of the graph?
The authors then re-estimate GMMS using an initial binarization result and iterate the graph cut over new data and smoothness term, until convergence.
Q12. What is the main difference between the two methods?
But these methods lack a principled formulation of the binarization problem of complex colour documents, and hence can not be generalized.