Document image binarization using a discriminative structural classifier

Ahmadi, Ehsan; Azimifar, Zohreh; Shams, Maryam; Famouri, Mahmoud; Shafiee, Mohammad Javad

doi:10.1016/j.patrec.2015.06.008

Cited by 27 publications

(9 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Markov random fields (MRFs) [28] and conditional random fields (CRFs) [29] are used for degraded document image binarization. Howe [30,31] presents an energy-based segmentation that uses graph cut optimization to solve the energy minimization problem of the objective function, which combines the Laplacian operator and the Canny edge detector.…”

Section: Related Workmentioning

confidence: 99%

DP-LinkNet: A convolutional network for historical document image binarization

2021

KSII TIIS

View full text Add to dashboard Cite

Document image binarization is an important pre-processing step in document analysis and archiving. The state-of-the-art models for document image binarization are variants of encoder-decoder architectures, such as FCN (fully convolutional network) and U-Net. Despite their success, they still suffer from three limitations: (1) reduced feature map resolution due to consecutive strided pooling or convolutions, (2) multiple scales of target objects, and (3) reduced localization accuracy due to the built-in invariance of deep convolutional neural networks (DCNNs). To overcome these three challenges, we propose an improved semantic segmentation model, referred to as DP-LinkNet, which adopts the D-LinkNet architecture as its backbone, with the proposed hybrid dilated convolution (HDC) and spatial pyramid pooling (SPP) modules between the encoder and the decoder. Extensive experiments are conducted on recent document image binarization competition (DIBCO) and handwritten document image binarization competition (H-DIBCO) benchmark datasets. Results show that our proposed DP-LinkNet outperforms other state-of-the-art techniques by a large margin. Our implementation and the pre-trained models are available at https://github.com/beargolden/DP-LinkNet.

show abstract

Section: Related Workmentioning

confidence: 99%

DP-LinkNet: A convolutional network for historical document image binarization

2021

KSII TIIS

View full text Add to dashboard Cite

show abstract

“…Gatos et al [39] implemented Wiener filtering in the spatial domain as where 2 (i, j) is a local estimate of the variance of additive Gaussian noise. In [39], 2…”

Section: Noise Removalmentioning

confidence: 99%

“…dev. AdOtsu [95] Local threshold Local version of Otsu Lu [82] Edge based Local thresholding near edges after background removal Su [162] Edge based Filters canny edges using local contrast Jia [53] Edge based Detecting symmetry of stroke edges Valizadeh [166] Edge based Adaptive water flow model Hadjadj [43] Edge based Active contours initialized using contrast edges [162] Rivest [139] Edge based Level-set method Nafchi [104] Image transform Threshold filter response in frequency domain Sehad [147] Image transform Performs background removal using Fourier Transform Zemouri [177] Image transform Uses Contourlet Transform to smooth image FAIR [73] Mixture model Ensemble of MoG with post-filtering Hedjam [47] Mixture model MoG with spatially varying Σ k Mishra [91] Mixture model 10-component MoG for foreground color variation Mitainoudis [93] Mixture model MoG over pairs of intensity co-occurrences Ramirez [138] Mixture model Mixture of log-normal distributions outperforms MoG Howe [50] CRF Laplacian unary term and pairwise Canny-based term Ayyalasomayajula [7] CRF Pairwise terms based on an initial binarization Peng [120] CRF Pairwise terms based on an initial foreground skeleton Su [161] CRF Uses CRF to classify uncertain pixels Ahmadi [2] CRF Learns linear combination of feature functions GiB [13] Game theory Extracts features for clustering using game theory Hamza [44] Shallow ML Self-organizing map to cluster pixels Rabelo [132] Shallow ML MLP to classify pixels using local mean Kefali [58] Shallow ML MLP using local intensities and global statistic features Pastor [118] Shallow ML MLP with F-measure loss function Kasmin [56] Shallow ML Ensemble of 8 SVMs Wu [174] Shallow ML Random forest trained on a rich feature set Pastor [119] Deep learning First CNN for binarization Peng [121] Deep learning Encoder-decoder FCN trained on synthetic data Calvo-Zaragoza ...…”

Section: Otsumentioning

confidence: 99%

“…The previously described CRFs use handcrafted energy functions and do not learn parameters. In contrast, Ahmadi et al [2] define E i and E ij as a linear combination of feature functions based on window statistics, histogram of oriented gradients (HOG) [30], local binary patterns (LBP) [113], and Canny edges [22]. The linear combination weights (feature importance) are then learned from training data and fixed for novel test images.…”

Section: Conditional Random Fieldsmentioning

confidence: 99%

See 1 more Smart Citation

Historical Document Image Binarization: A Review

Tensmeyer

Martinez

2020

SN COMPUT. SCI.

View full text Add to dashboard Cite

This review provides a comprehensive view of the field of historical document image binarization with a focus on the contributions made in the last decade. After the introduction of a standard benchmark dataset with the 2009 Document Image Binarization Contest, research in the field accelerated. Besides the standard methods for image thresholding, preprocessing, and post-processing, we review the literature on methods such as statistical models, pixel classification with learning algorithms, and parameter tuning. In addition to reviewing binarization algorithms, we discuss the available public datasets and evaluation metrics, including those that require pixel-level ground truth and those that do not. We conclude with recommendations for future work.

show abstract

“…There are several applications of old manuscript recognition such as Tamil text manuscripts, old Damascus Manuscripts, Farsi Manuscripts, Greek Manuscripts, Arabic Manuscripts. They have proposes a statistical framework for degraded document binarization images based on the concept of conditional random fields (CRFs) [1]. The CRFs are discriminative graphical model which conditional distribution model and used in structural classifications.…”

Section: Introductionmentioning

confidence: 99%

Image Enhancement Background for High Damage Malay Manuscripts using Adaptive Threshold Binarization

Yahya

Omar

Abdullah

et al. 2018

Int. J. Adv. Sci. Eng. Inf. Technol.

View full text Add to dashboard Cite

Jawi Manuscripts handwritten which are kept at Malaysia National Library (MNL), has aged over decades. Regardless of the intensive sustainable process conducted by MNL, these manuscripts are still not maintained in good quality, and neither can easily be read nor better view. Even thought, many states of the art methods have developed for image enhancement, none of them can solve extremely bad quality manuscripts. The quality of old Malay Manuscripts can be categorize into three types, namely: the background image is uneven, image effects and image effects expand patch. The aim of this paper is to discuss the methods used to value add the quality of the manuscript. Our propose methods consist of several main methods, such as: Local Adaptive Equalization, Image Intensity Values, Automatic Threshold PP, and Adaptive Threshold Filtering. This paper is intend to achieve a better view image that geared to ease reading. Error Bit Phase achievement (TKB) has a smaller error value for proposed method (Adaptive Threshold Filtering Process / PAM) namely 0.0316 compared with Otsu's Threshold Method / MNAO, Binary Threshold Value Method / MNAP, and Automatic Local Threshold Value Method / MNATA. The precision achievement (namely on ink bleed images) is using a proposed method more than 95% is compared with the state of the art methods MNAO, MNAP, MNATA and their performances are 75.82%, 90.68%, and 91.2% subsequently. However, this paper's achievement is using a proposed method / PAM, MNAO, MNAP, and MNATA for correspondingly the image of ink bleed case are 45.74%, 54.80%, 53.23% and 46.02%. Conclusion, the proposed method produces a better character shape in comparison to other methods.

show abstract

Document image binarization using a discriminative structural classifier

Cited by 27 publications

References 28 publications

DP-LinkNet: A convolutional network for historical document image binarization

DP-LinkNet: A convolutional network for historical document image binarization

Historical Document Image Binarization: A Review

Image Enhancement Background for High Damage Malay Manuscripts using Adaptive Threshold Binarization

Contact Info

Product

Resources

About