Search

Color image binarization plays a pivotal role in image preprocessing work and significantly impacts subsequent tasks, particularly for text recognition. This paper concentrates on document image binarization (DIB), which aims to separate an image into a foreground (text) and background (non-text content). We thoroughly analyze conventional and deep-learning-based approaches and conclude that prevailing DIB methods leverage deep learning technology. Furthermore, we explore the receptive fields of pre- and post-network training to underscore the Transformer model's advantages. Subsequently, we introduce a lightweight model based on the U-Net structure and enhanced with the MobileViT module to capture global information features in document images better. Given its adeptness at learning both local and global features, our proposed model demonstrates competitive performance on two standard datasets (DIBCO2012 and DIBCO2017) and good robustness on the DIBCO2019 dataset. Notably, our proposed method presents a straightforward end-to-end model devoid of additional image preprocessing or post-processing, eschewing the use of ensemble models. Moreover, its parameter count is less than one-eighth of the model, which achieves the best results on most DIBCO datasets. Finally, two sets of ablation experiments are conducted to verify the effectiveness of the proposed binarization model. [ABSTRACT FROM AUTHOR]

Image denoising attempts to restore images that have been degraded. Historical document denoising is specially challenging because there is considerable background noise or variation in contrast and illumination in handwritten literature and the first times of the printing press. The main objective of this work is to propose a new method for historical document denoising based on an Attentive Generative Adversarial Network (Attentive-GAN). Our proposed model for historical document denoising is named Doc-Attentive GAN , and it employs an attention map generated by a deep network to help the generator to learn and focus on the modification between the target image and its noisy version. It has been trained and tested with different historical document collections such as well-known DIBCO datasets, Arabic Historical Documents from the Tunisian National Library, and Incunabula books. The experiments demonstrate a clear improvement in the visual quality of the images obtained by Doc-Attentive-GAN with respect to the state-of-the-art. [ABSTRACT FROM AUTHOR]

Text recognition has benefited considerably from deep learning research, as well as the preprocessing methods included in its workflow. Identity documents are critical in the field of document analysis and should be thoroughly researched in relation to this workflow. We propose to examine the link between deep learning-based binarization and recognition algorithms for this sort of documents on the MIDV-500 and MIDV-2020 datasets. We provide a series of experiments to illustrate the relation between the quality of the collected images with respect to the binarization results, as well as the influence of its output on final recognition performance. We show that deep learning-based binarization solutions are affected by the capture quality, which implies that they still need significant improvements. We also show that proper binarization results can improve the performance for many recognition methods. Our retrained U-Net-bin outperformed all other binarization methods, and the best result in recognition was obtained by Paddle Paddle OCR v2.

Document Image Binarization is one of the image enhancement techniques and has potential applications in the field of Document Image Analysis and Recognition (DIAR). During the DIAR process, different types of noise such as uneven illumination, clutter, margin, skew, bleed-through and show-through are removed. However, the removal of show-through noise is a challenging task because it affects mostly the document image quality and readability. In this work, we have designed and developed a model-based point processing operation, which is implemented in the Altera Cyclone® V DE1-SoC for removing the show-through noise and enhancing the degraded document image quality. The Altera Cyclone® V DE1-SoC board was chosen for this study due to its performance, size compatibility, and real-time implementation, which are better than the programmable DSP chips. The Pixel/Point processing operations were implemented using the DSP builder tool, which boost-up better execution of computational operations involved in complex algorithms. To implement the proposed algorithm, we have developed the board library file for Altera Cyclone® V DE1-SoC series 5CSEMA5F31C6 board in DSP builder and tested on various document images. The calculated quality measures of the proposed algorithm tested on various document images in the FPGA board exhibited better results in terms of document image readability, quality, processing speed, and memory size. Further, the performance of the proposed algorithms was studied in different scanned document images dataset as well as with the other traditional techniques. The results of this study witnessed that the proposed model-based point processing methods performs very well than the other methods.

Document Image Binarization is one of the image enhancement techniques and has potential applications in the field of Document Image Analysis and Recognition (DIAR). During the DIAR process, different types of noise such as uneven illumination, clutter, margin, skew, bleed-through and show-through are removed. However, the removal of show-through noise is a challenging task because it affects mostly the document image quality and readability. In this work, we have designed and developed a model-based point processing operation, which is implemented in the Altera Cyclone® V DE1-SoC for removing the show-through noise and enhancing the degraded document image quality. The Altera Cyclone® V DE1-SoC board was chosen for this study due to its performance, size compatibility, and real-time implementation, which are better than the programmable DSP chips. The Pixel/Point processing operations were implemented using the DSP builder tool, which boost-up better execution of computational operations involved in complex algorithms. To implement the proposed algorithm, we have developed the board library file for Altera Cyclone® V DE1-SoC series 5CSEMA5F31C6 board in DSP builder and tested on various document images. The calculated quality measures of the proposed algorithm tested on various document images in the FPGA board exhibited better results in terms of document image readability, quality, processing speed, and memory size. Further, the performance of the proposed algorithms was studied in different scanned document images dataset as well as with the other traditional techniques. The results of this study witnessed that the proposed model-based point processing methods performs very well than the other methods. [ABSTRACT FROM AUTHOR]

The efficient extraction of text information from the background in degraded color document images is an important challenge in the preservation of ancient manuscripts. The imperfect preservation of ancient manuscripts has led to different types of degradation over time, such as page yellowing, staining, and ink bleeding, seriously affecting the results of document image binarization. This work proposes an effective three-stage network method to image enhancement and binarization of degraded documents using generative adversarial networks (GANs). Specifically, in Stage-1, we first split the input images into multiple patches, and then split these patches into four single-channel patch images (gray, red, green, and blue). Then, three single-channel patch images (red, green, and blue) are processed by the discrete wavelet transform (DWT) with normalization. In Stage-2, we use four independent generators to separately train GAN models based on the four channels on the processed patch images to extract color foreground information. Finally, in Stage-3, we train two independent GAN models on the outputs of Stage-2 and the resized original input images (512 × 512) as the local and global predictions to obtain the final outputs. The experimental results show that the Avg-Score metrics of the proposed method are 77.64, 77.95, 79.05, 76.38, 75.34, and 77.00 on the (H)-DIBCO 2011, 2013, 2014, 2016, 2017, and 2018 datasets, which are at the state-of-the-art level. The implementation code for this work is available at https://github.com/abcpp12383/ThreeStageBinarization. • Introduces a three-stage network for enhancement and binarization of color degraded images. • Achieves state-of-the-art performance on multiple benchmark datasets. • Demonstrates binarized images using DWT and normalization are closer to Ground-Truth. [ABSTRACT FROM AUTHOR]

Abstract Binarization plays an important role in document analysis and recognition (DAR) systems. In this paper, we present our winning algorithm in ICFHR 2018 competition on handwritten document image binarization (H-DIBCO 2018), which is based on background estimation and energy minimization. First, we adopt mathematical morphological operations to estimate and compensate the document background. It uses a disk-shaped structuring element, whose radius is computed by the minimum entropy-based stroke width transform (SWT). Second, we perform Laplacian energy-based segmentation on the compensated document images. Finally, we implement post-processing to preserve text stroke connectivity and eliminate isolated noise. Experimental results indicate that the proposed method outperforms other state-of-the-art techniques on several public available benchmark datasets.

Text is the most crucial element in a document image but is often disconnected in document image binarization. Most of the previous methods based on deep learning do not focus on structure information such as stroke boundary, leading to disconnected strokes when the stroke is ambiguous or weak. In this paper, we propose a multi-task learning with an auxiliary task for learning stroke boundary features in an adversarial manner. The learned boundary features are integrated into the main task for the binarization. Specifically, in the first step, in addition to using shared global location features with the main task, the auxiliary task leverages additional local edges to obtain stroke boundary features. In the second step, we use adversarial loss based on boundary ground truth to supervise the obtained stroke boundary feature in the auxiliary task. The adversarial training is to embed expert knowledge, especially structure information, in the model. In the third step, the learned boundary feature from the auxiliary task supports the main task directly. The fusion module of the main task refines the final binarized image. Experiments show that our method achieves better-preserved stroke and better performance than existing methods on benchmark H-DBCO and DIBCO datasets.

Preprocessing for degraded document images can improve their binarization result. Sharpening and illumination compensation are effective methods in preprocessing. We find the degree of sharpening has different effects on the different stroke width. As the degree of sharpening increases, the thin strokes retained more information in the binarization results, while the thick strokes gradually appear to be broken. Aiming at this problem, we propose a local adaptive sharpening method. The stroke width estimation algorithm is utilized to estimate the stroke width in the local region. Local adaptive sharpening is performed to solve the problem of thick stroke fracture and retain more information of thin strokes. In addition, comparing with the weakly illuminated document images, the sharpening effects on strongly illuminated document images are more prominent, and the binarization result is better. Therefore, appropriate illumination compensation is used for weakly illuminated document images. We further propose a preprocessing method for degraded document image using local adaptive sharpening and illumination compensation. The experimental results show that our proposed method restores more detail information and keeps the thick stroke information in binarization result. Our method outperforms U-Net without preprocessing by 0.36% FM scores on DIBCO2016, 1.09% FM scores on DIBCO2017 and 1.42% FM scores on DIBCO2018. U-Net, Sauvola and OTSU combined with our LASIC outperform themselves by 1.42%, 0.29% and 5.41% FM scores on DIBCO2018. And our LASIC method outperforms other preprocessing methods by 0.1% to 1.05% FM scores on DIBCO2016-DIBCO2018. [ABSTRACT FROM AUTHOR]

Convolutional neural networks (CNNs) have previously been broadly utilized to binarize document images. These methods have problems when faced with degraded historical documents. This paper proposes the utilization of CNNs to identify foreground pixels using novel input-generated multichannel images. To create the images, the original source image is decomposed into wavelet subbands. Then, the original image is approximated by each subband separately, and finally, the multichannel image is constituted by arranging the original source image (grayscale image) as the first channel and the approximated image by each subband as the remaining channels. To achieve the best results, two scenarios are considered, that is, two-channel and four-channel images, and then fed into two types of CNN architectures, namely, single and multiple streams. To investigate the effect of the multichannel images proposed as network inputs, the CNNs used in the architectures are three popular networks, namely, U-net, SegNet, and DeepLabv3+. The experimental results of the scenarios demonstrate that our method is more successful than the three CNNs when trained by the original source images and proves competitive performance in comparison with state-of-the-art results using the DIBCO database.

Binarization plays an important role in document analysis and recognition (DAR) systems. In this paper, we present our winning algorithm in ICFHR 2018 competition on handwritten document image binarization (H-DIBCO 2018), which is based on background estimation and energy minimization. First, we adopt mathematical morphological operations to estimate and compensate the document background. It uses a disk-shaped structuring element, whose radius is computed by the minimum entropy-based stroke width transform (SWT). Second, we perform Laplacian energy-based segmentation on the compensated document images. Finally, we implement post-processing to preserve text stroke connectivity and eliminate isolated noise. Experimental results indicate that the proposed method outperforms other state-of-the-art techniques on several public available benchmark datasets. [ABSTRACT FROM AUTHOR]

Data is critical in deep learning but the scarcity of data often occurs in research, especially in the preparation of the paired training data. In this paper, document image binarization with unpaired data is studied by introducing adversarial learning, excluding the need for supervised or labeled datasets. However, the simple extension of the previous unpaired training to binarization inevitably leads to poor performance compared to paired data training. Thus, a new deep learning approach is proposed by introducing a multi-diversity of higher quality generated images. In this paper, a two-stage model is proposed that comprises the generative adversarial network (GAN) followed by the U-net network. In the first stage, the GAN uses the unpaired image data to create paired image data. With the second stage, the generated paired image data are passed through the U-net network for binarization. Thus, the trained U-net becomes the binarization model during the testing. The proposed model has been evaluated over the publicly available DIBCO dataset and it outperforms other techniques on unpaired training data. The paper shows the potential of using unpaired data for binarization, for the first time in the literature, which can be further improved to replace paired data training for binarization in the future. [ABSTRACT FROM AUTHOR]

Low quality document images have various degradation factors, such as page stains, ink bleed-through and background texture. This paper proposed a novel document image binarization algorithm based on background estimation and U -Net. The algorithm first performed image contrast enhancement, and estimated the document image background via morphological closing operations . It then adopted a fully convolutional network, namely the U-Net, to extract the foreground text from the document background . Finally, it used the global optimal thresholding method to obtain the resulting binary image . Experimental results show that in the 2016 and 2017 DIBCO the proposed method outperforms other state-of-the-art document image binarization algorithms in terms of F-measure, pseudo F-measure, PSNR and DRD, with 5. 58%, 2 . 47%, 0. 86 dB and 1. 19% . [ABSTRACT FROM AUTHOR]

Abstract This paper presents a textline detection method for degraded historical documents. Our method follows a conventional two-step procedure that the binarization is first performed and then the textlines are extracted from the binary image. In order to address the challenges in historical documents such as document degradation, structure noise, and skews, we develop new methods for the binarization and textline extraction. First, we improve the performance of binarization by detecting the non-text regions and processing only text regions. We also improve the textline detection method by extracting main textblock and compensating the skew angle and writing style. Experimental results show that the proposed method yields the state-of-the-art performance for several datasets.

Document image binarization is a challenging task because of combined degradation in a document. In this study, a new binarization method is proposed for binarizing an ancient document with combined degradation. The proposed method comprises the following four stages: histogram analysis, contrast enhancement, local adaptive thresholding, and artifact removal. In histogram analysis, a new approach is applied to establish a uniform background. Next, the image contrast is enhanced using a new contrast enhancement, and then the document is binarized using a novel local adaptive thresholding. Artifacts from the binarization process are removed in the artifact removal stage. Finally, an experiment is conducted using one private and four public datasets and by simulating the proposed method with and without contrast enhancement. The results showed that the proposed method is faster and more effective compared to other state-of-the-art procedures for binarizing ancient documents.

Abstract Binarization is a fundamental problem in document image analysis systems. Different from current thresholding techniques, a novel variational model is proposed for noise robust document image binarization in this work, which is inspired by two classical variational models that have been successfully applied in image segmentation and denoising. In our variational model, the energy functional consists of three terms: data fidelity term, binary classification term and regularization term. As a result, the proposed model is capable of performing image binarization and suppressing noise simultaneously. Concretely, we firstly design a variational model for the original document image, the minimizer of which is our desired binarization result. Secondly, the gradient descent flow equation of our model is derived by means of variational principle. Lastly, a simple finite difference scheme, time forward and space center difference, is employed to solve the gradient descent flow equation. Extensive experiments are conducted on three types of document image datasets to validate our model qualitatively and quantitatively. The experiment results not only demonstrate the effectiveness of our approach, but also verify its noise and illumination robustness. [ABSTRACT FROM AUTHOR]

This paper presents a support vector machine (SVM) based method for degraded historical document image binarization. Given a degraded historical document image, the proposed method first segments the image into w  ×  w regions and implements a local contrast enhancement in each image block. We then use a SVM to select an optimal global threshold for binarization of each image block. Finally, the entire image is further binarized by a locally adaptive thresholding method. The proposed method has been evaluated over the recent Document Image Binarization Competition (DIBCO) datasets. The experimental results show that our proposed method outperforms other state-of-the-art techniques in terms of F-measure, NRM, DRD, and MPM. [ABSTRACT FROM AUTHOR]

This paper presents an effective approach for the local threshold binarization of degraded document images. We utilize the structural symmetric pixels (SSPs) to calculate the local threshold in neighborhood and the voting result of multiple thresholds will determine whether one pixel belongs to the foreground or not. The SSPs are defined as the pixels around strokes whose gradient magnitudes are large enough and orientations are symmetric opposite. The compensated gradient map is used to extract the SSP so as to weaken the influence of document degradations. To extract SSP candidates with large magnitudes and distinguish the faint characters and bleed-through background, we propose an adaptive global threshold selection algorithm. To further extract pixels with opposite orientations, an iterative stroke width estimation algorithm is applied to ensure the proper size of neighborhood used in orientation judgement. At last, we present a multiple threshold vote based framework to deal with some inaccurate detections of SSP. The experimental results on seven public document image binarization datasets show that our method is accurate and robust compared with many traditional and state-of-the-art document binarization approaches based on multiple evaluation measures. [ABSTRACT FROM AUTHOR]

The binarization of degraded document images is a challenging problem in terms of document analysis. Binarization is a classification process in which intra-image pixels are assigned to either of the two following classes: foreground text and background. Most of the algorithms are constructed on low-level features in an unsupervised manner, and the consequent disenabling of full utilization of input-domain knowledge considerably limits distinguishing of background noises from the foreground. In this paper, a novel supervised-binarization method is proposed, in which a hierarchical deep supervised network (DSN) architecture is learned for the prediction of the text pixels at different feature levels. With higher-level features, the network can differentiate text pixels from background noises, whereby severe degradations that occur in document images can be managed. Alternatively, foreground maps that are predicted at lower-level features present a higher visual quality at the boundary area. Compared with those of traditional algorithms, binary images generated by our architecture have cleaner background and better-preserved strokes. The proposed approach achieves state-of-the-art results over widely used DIBCO datasets, revealing the robustness of the presented method. [ABSTRACT FROM AUTHOR]

This paper presents a textline detection method for degraded historical documents. Our method follows a conventional two-step procedure that the binarization is first performed and then the textlines are extracted from the binary image. In order to address the challenges in historical documents such as document degradation, structure noise, and skews, we develop new methods for the binarization and textline extraction. First, we improve the performance of binarization by detecting the non-text regions and processing only text regions. We also improve the textline detection method by extracting main textblock and compensating the skew angle and writing style. Experimental results show that the proposed method yields the state-of-the-art performance for several datasets. [ABSTRACT FROM AUTHOR]

Document binarization is an important technique in document image analysis and recognition. Generally, binarization methods are ineffective for degraded images. Several binarization methods have been proposed; however, none of them are effective for historical and degraded document images. In this paper, a new binarization method is proposed for degraded document images. The proposed method based on the variance between pixel contrast, it consists of four stages: pre-processing, geometrical feature extraction, feature selection, and post-processing. The proposed method was evaluated based on several visual and statistical experiments. The experiments were conducted using five International Document Image Binarization Contest benchmark datasets specialized for binarization testing. The results compared with five adaptive binarization methods: Niblack, Sauvola thresholding, Sauvola compound algorithm, NICK, and Bataineh. The results show that the proposed method performs better than other methods in all binarization cases. [ABSTRACT FROM AUTHOR]

Image binarization refers to convert gray-level images into binary ones, and many binarization algorithms have been developed. The related algorithms can be classified as either high quality computation or high speed performance. This paper presents an algorithm that ensures both benefits at the same time. The proposed algorithm intelligently segments input images into several different sized sub-images by using a Sobel like matrix. After which each sub-image will be classified into background set or foreground set according to it's feature. Finally the foreground set sub-images will be binarized by Otsu's method independently. Experimental results reveal that our algorithm provides the appropriate quality with the medium speed. [ABSTRACT FROM AUTHOR]

Binarization is one of the key initial steps in image analysis and system understanding. Different types of document degradations make the binarization a very challenging task. This paper proposes a statistical framework for binarizing degraded document images based on the concept of conditional random fields (CRFs). The CRFs are discriminative graphical models which model conditional distribution and are used in structural classifications. The distribution of binarized images given the degraded ones is modelled with respect to a set of informative features extracted for all sites of the document image. The recent marginal based learning method [5] is used for the estimation of parameters of the model. The proposed graphical framework enables the depending labelling of all the sites of image despite the independent pixel-by-pixel binarization of other methods. The performance of our system is evaluated on different document image datasets and is compared with several well-known binarization methods. Experimental results show comparable performance with respect to other state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Binarization of images of old documents is considered a challenging task due to the wide diversity of degradation effects that can be found. To deal with this, many algorithms whose performance depends on an appropriate choice of their parameters have been proposed. In this work, it is investigated the application of a racing procedure based on a statistical approach, named I/F-Race, to suggest the parameters for two binarization algorithms reasoned (i) on the perception of objects by distance (POD) and (ii) on the POD combined with a Laplacian energy-based technique. Our experiments show that both algorithms had their performance statistically improved outperforming other recent binarization techniques. The second proposal presented herein ranked first in H-DIBCO (Handwritten Document Image Binarization Contest) 2014. [ABSTRACT FROM AUTHOR]

Historical document restoration has always been a challenging need for information acquisition and conversion to a stable and portable format. Document image binarization, is an important pre-processing phase in document image analysis and processing of such historical documents. It has never been an easy task accounting to the difficulty in choosing a threshold value when the document image suffers from noises due present in the original document due to its degradation, ageing of the paper, other unwanted impurities, background images, bleed-through, and so on. Inconsistency in the darkness of the letters in handwritten documents adds to the difficulty. Though there are many algorithms that have been proposed for document image binarization, there has not been an effective algorithm which can efficiently binarize all kind of documents. In this paper we introduce a novel method to perform document image binarization using bit-plane slicing. As per this approach, the 8 bit planes of the gray image are extracted and processed separately, at the end of which, the results are combined to give the final binarized output. This method works well for all kinds of historical documents except those with both, less noise and low contrast. [ABSTRACT FROM AUTHOR]

Abstract: There are many challenges addressed in handwritten document image binarization, such as faint characters, bleed-through and large background ink stains. Usually, binarization methods cannot deal with all the degradation types effectively. Motivated by the low detection rate of faint characters in binarization of handwritten document images, a combination of a global and a local adaptive binarization method at connected component level is proposed that aims in an improved overall performance. Initially, background estimation is applied along with image normalization based on background compensation. Afterwards, global binarization is performed on the normalized image. In the binarized image very small components are discarded and representative characteristics of a document image such as the stroke width and the contrast are computed. Furthermore, local adaptive binarization is performed on the normalized image taking into account the aforementioned characteristics. Finally, the two binarization outputs are combined at connected component level. Our method achieves top performance after extensive testing on the DIBCO (Document Image Binarization Contest) series datasets which include a variety of degraded handwritten document images. [Copyright &y& Elsevier]

• We propose a strict convex variational level set model for document binarization, and it has a unique global minimizer. • It is an initialization-flexible model, and the evolution termination condition can be set via level set function. • Our model can deal with many kinds of degradations, such as, low contrast, bleed-through, faint characters, texture. • Our model can achieve comparable or better performance. Moreover, it is efficient and robust to noise to some extent. Document image binarization is a significant stage in the optical character recognition system. Different from previous binarization approaches, in this paper, we propose a novel and convex variational level set model for document image binarization. Our energy functional is comprised of two terms: data term and fidelity term. We prove that our model is strictly convex and has a unique global minimum solution, which enables us to set the evolution termination criterion by the normalized step difference energy that measures the convergence state of level set function. We experimentally demonstrate the advantage of the fidelity term and show the merit of level set initialization robustness. In addition, the convergence of the alternative minimization algorithm for solving our model is analyzed. Extensive experiments are conducted on JM dataset, representative degraded document images and DIBCO series datasets to evaluate our model qualitatively and quantitatively. The experiment results verify that our model is effective to deal with most kinds of degraded images. Compared with four evolution and six non-evolution based binarization methods, our model could achieve better or competitive performance in terms of four metrics. [ABSTRACT FROM AUTHOR]

Abstract: An original binarization method for document images acquired under non-uniform illumination conditions was proposed in this paper. The Curvelet transform and Otsu''s method were combined to binarize the non-uniform illuminated images. The non-uniform illumination image was decomposed by the Curvelet. And, the Curvelet coefficients were enhanced by nonlinear functions. Then, the reconstructed image was processed by Otsu''s binarization method. The experiment results of our and the others methods were shown and discussed. [Copyright &y& Elsevier]

Document image binarization is of great importance in the document image analysis and recognition pipeline since it affects further stages of the recognition process. The evaluation of a binarization method aids in studying its algorithmic behavior, as well as verifying its effectiveness, by providing qualitative and quantitative indication of its performance. This paper addresses a pixel-based binarization evaluation methodology for historical handwritten/machine-printed document images. In the proposed evaluation scheme, the recall and precision evaluation measures are properly modified using a weighting scheme that diminishes any potential evaluation bias. Additional performance metrics of the proposed evaluation scheme consist of the percentage rates of broken and missed text, false alarms, background noise, character enlargement, and merging. Several experiments conducted in comparison with other pixel-based evaluation measures demonstrate the validity of the proposed evaluation scheme. [ABSTRACT FROM PUBLISHER]

Connections in image processing are an important notion that describes how pixels can be grouped together according to their spatial relationships and/or their gray-level values. In recent years, several works were devoted to the development of new theories of connections among which hyperconnection (h-connection) is a very promising notion. This paper addresses two major issues of this theory. First, we propose a new axiomatic that ensures that every h-connection generates decompositions that are consistent for image processing and, more precisely, for the design of h-connected filters. Second, we develop a general framework to represent the decomposition of an image into h-connections as a tree that corresponds to the generalization of the connected component tree. Such trees are indeed an efficient and intuitive way to design attribute filters or to perform detection tasks based on qualitative or quantitative attributes. These theoretical developments are applied to a particular fuzzy h-connection, and we test this new framework on several classical applications in image processing, i.e., segmentation, connected filtering, and document image binarization. The experiments confirm the suitability of the proposed approach: It is robust to noise, and it provides an efficient framework to design selective filters. [ABSTRACT FROM PUBLISHER]

Abstract: Binary image representation is essential format for document analysis. In general, different available binarization techniques are implemented for different types of binarization problems. The majority of binarization techniques are complex and are compounded from filters and existing operations. However, the few simple thresholding methods available cannot be applied to many binarization problems. In this paper, we propose a local binarization method based on a simple, novel thresholding method with dynamic and flexible windows. The proposed method is tested on selected samples called the DIBCO 2009 benchmark dataset using specialized evaluation techniques for binarization processes. To evaluate the performance of our proposed method, we compared it with the Niblack, Sauvola and NICK methods. The results of the experiments show that the proposed method adapts well to all types of binarization challenges, can deal with higher numbers of binarization problems and boosts the overall performance of the binarization. [Copyright &y& Elsevier]