A robust multi stage technique for image binarization of degraded historical documents

문서 이미지의 이진화는 문서 인식의 이전 단계에서 주로 사용되며, 이진화의 성공 여부에 따라 문서 인식의 결과에 영향을 미치는 중요한 단계로 볼 수 있다. 지금까지 문서 이미지를 이진화 하기 위한 다양한 기법들이 연구되었지만, 문서 이미지의 상태에 따라 그 결과는 다양하다. 본 논문에서는 객체 추출에 많이 이용되는 MSER(Maximally Stable Extremal Region)을 이용하여 문서 이미지를 이진화하는 기법을 제안한다. 먼저 문서 이미지에서 MSER 객체를 추출한다. 추출된 MSER 객체는 그 자체로 문서 이미지 이진화에 사용되기는 어렵기 때문에 사용하기 적합한 형태로 변경되는 과정을 거친다. 그리고 최종 MSER 객체와 문서 이미지로부터 추출한 대비 이진 이미지를 이용하여 최종 이진 이미지를 계산한다. 실험결과는 본 논문에서 제안한 방법이 문서 이미지의 이진화에 유용함을 보여준다. Document image binarization is largely used as previous stage of document recognition. And the result of document recognition is much affected from the result of document image binarization. There were many studies to binarize document images. The results of previous studies for document image binarization is varied according to the state of document images. In this paper, we propose a technique for document image binarization using MSER that is applied to extract objects from an image. At first, raw MSER objects are extracted from a document image. Because the raw MSER objects cannot be used for document image binarization, the extracted raw MSER objects are modified. Then the final MSER objects are used for document image binarization with the contrast image that is extracted from the document image. Experimental results show that the proposed technique is useful for document image binarization.

Document image binarization, especially old handwritten documents, is a very important yet challenging task. There are various bottlenecks for binarizing historical documents due to different types of degradation present imultaneously such as back impression, ink bleed through, faded colours, and wear and tear of the writing media. We consider these degradation as various types of noise in the document image. Here we have proposed a 2D morphological network which consists of basic morphological operation like dilation and erosion to perform our targeted task. The network also includes linear combination of output from dilation and erosion operations. The aforementioned 2D morphological network is applied for image binarization, where the structuring elements (SEs) and the weights of the linear combination layer are learned through back-propagation. The proposed network has been evaluated on DIBCO 2017 and H-DIBCO 2018 and ISI-Letter dataset. Our results show more convincing as compared to the results of other state-of-the-art methods. Though the network is developed for old handwritten documents, it may be tuned to work for image processing task. The source code can be found here https://github.com/ranjanZ/ICDAR_Binarization.

Document image binarization has been a long standing problem for unconstrained document images. Although various thresholding algorithms have been developed over the years, problems associated with strong noise, complex patterns, poor contrast, and variable modalities in gray-scale histograms still limit the performance of document image analysis systems. Given the unpredictable nature of these image attributes, few thresholding algorithms work consistently well for document image binarization. This dissertation presents texture feature based thresholding algorithms to address these difficulties. The philosophy of our thresholding approach is that the texture domain knowledge of document images is important to judge the binarization quality and thus guide the binarization process; that is, suitably defined texture features of document images can be used to assist the optimal threshold selection. Our thresholding scheme consists of three steps. First, candidate thresholds are produced through the iterative use of Otsu's algorithm. Second, texture features associated with each candidate threshold are extracted from the run-length histogram of the accordingly binarized image. Third, the optimal threshold is selected so that the most desirable document texture features are preserved. This thresholding scheme was implemented in both global and adaptive modes. With our program design the algorithms require only one image scan pass, facilitating their hardware implementation for a commercial system. Experimental results with 9000 machine printed address blocks from an unconstrained US mail stream demonstrated that over 99.6% of the images were well binarized by our thresholding method, which are appreciably better than those obtained by existing thresholding techniques. Also a system run with 500 difficult mail address blocks showed that an 8.1% higher character recognition rate was achieved by our algorithm in comparison to that by Otsu's algorithm.

Binarization is an important step in reading text documents automatically through optical character recognition. Old document images often suffer from degradations that make their binarization a challenging task. In this paper, a new binarization technique for degraded document images is presented. The proposed technique is based on active contours evolving according to intrinsic geometric measures of the document image. The image contrast that is defined by the local image maximum and minimum is used to automatically generate the initialization map of our active contour model; an average thresholding is also used to produce the final delineation and binarization. The proposed implementation benefits from the level set framework, which allows the simultaneous application of a large variety of forces at the stroke–background interface. Our binarization method involves the combination of those forces in a specific way. The efficiency of the proposed method is shown on both recent and historical document images of the Document Image Binarization Contest (DIBCO) datasets that include different types of degradations. The results are compared to a number of known techniques from the literature.

Document image binarization plays an important role in image segmentation and its effect directly impacts on the quality of the OCR recognition system. However, binarization is difficult for camera-based document images with poor contrast or illumination. In this paper, we propose a binarization algorithm, called NFCM, for camera-based document image. NFCM, a local threshold method, is a combination of Niblack algorithm and FCM (Fuzzy C-Means) algorithm. It is good at not only preserving the character stokes, but also alleviating the ghost artifacts. Comparative experiments show that NFCM can obtain favorable results with respect to the OCR performance.

Document image binarization is a crucial step towards optical character recognition and analysis. One common way to achieve image binarization is thresholding. Thresholding methods can be divided into global and local ones in terms of the regional information used in obtaining the threshold values. Both methods have their respective drawbacks. Global methods can not adapt to background variations while local methods have the problem of local widow size determination. Hybrid methods that combines both local and global thresholds and can alleviating these drawbacks. In this paper, the hybrid threshold method is utilized and trade-off between the local and global contents is determined using variational optimization. The proposed algorithm is tested on (H-)DIBCO benchmarks and has shown superior performance to one state-of-the-art document image binarization method.

Document image binarization is a crucial preporocessing step in Optical Character Recognition (OCR) systems, but its accuracy is often hindered by non-uniform illumination. This paper introduces YAM, a novel and computationally efficient binarization technique based on a hybrid thresholding strategy. YAM integrate both global image statistics and local neighbourhood analysis to robustly adapt to luminance variations. Experiments conducted on the WEZUT OCR dataset shows YAM demonstrated superior performance over traditional binarization methods, including Sauvola, Niblack, and Otsu, achieving an F-measure of text recognition of $97.54 \%$ and a word accuracy score of $97.74 \%$. YAM incorporates a box filter approach which makes it executes faster than recent binarization techniques like ZigZag. Both quantitative and qualitative results validate YAM offers a compelling balance between performance and efficiency as a practical and high-fidelity solution suitable for resource-constrained environments.

Document image binarization with cascaded generators of conditional generative adversarial networks

The binarization of image is an important stage in any document analysis system such as OCR. It converts the colored or grayscale images into monochromatic form to reduce the computational complexity in the next stages. In old document images in the presence of degradations (ink bleed, stains, smear, non-uniform illumination, low contrast, etc.) the separation of foreground and background becomes a challenging task. Most of the existing binarization techniques can handle only a subset of these degradations. We present a simple binarization method for old document images. The experimental results confirm that the proposed technique gives good binarization results in the presence of various degradations. It computes the Laplacian of an image to separate the foreground. The subtracted Laplacian image is binarized using a global threshold. Finally, the postprocessing using morphological functions is applied. The results are compared in terms of F-measure, PSNR, time complexity, and OCR based evaluations which shows that our method outperforms existing techniques like Niblack, Sauvola, Gatos, Zhou, NICK, Singh, and Bataineh.

This paper proposes an adaptive binarization method for the document image binarization acquired by an imaging phone. The used algorithm determines the local thresholds with the information from the global trend as well as the local details. As a consequence, the proposed method is good not only for preserving the fine details of the character structure, but also for alleviating noise. The effectiveness of the proposed method is illustrated using the results obtained with a Nokia imaging phone.

Image binarization is an important process in many computer-vision applications. This transforms the color space of the original image into black and white. Global thresholding is a quick and reliable way to achieve binarization, but it is inherently limited by image noise and uneven lighting. This paper introduces a global thresholding method that uses the results of classical global thresholding algorithms and other global image features to train a regression model via machine learning. We prove through nested cross-validation that the model can predict the best possible global threshold with an average F-measure of 90.86% and a confidence of 0.79%. We apply our approach to a popular computer vision problem, document image binarization, and compare popular metrics with the best possible values achievable through global thresholding and with the values obtained through the algorithms we used to train our model. Our results show a significant improvement over these classical global thresholding algorithms, achieving near-perfect scores on all the computed metrics. We also compared our results with state-of-the-art binarization algorithms and outperformed them on certain datasets. The global threshold obtained through our method closely approximates the ideal global threshold and could be used in a mixed local-global approach for better results.

Document image binarization classifies each pixel in an input document image as either foreground or background under the assumption that the document is pseudo binary in nature. However, noise introduced during acquisition or due to aging or handling of the document can make binarization a challenging task. This paper presents a novel game theory inspired binarization technique for degraded document images. A two-player, non-zero-sum, non-cooperative game is designed at the pixel level to extract the local information, which is then fed to a K-means algorithm to classify a pixel as foreground or background. We also present a preprocessing step that is performed to eliminate the intensity variation that often appears in the background and a post-processing step to refine the results. The method is tested on seven publicly available datasets, namely, DIBCO 2009-14 and 2016. The experimental results show that GiB (Game theory Inspired Binarization) outperforms competing state-of-the-art methods in most cases.

Digitization of document images using OCR based systems is adversely affected if the image of the document contains distortion (warping). Often, costly and precisely calibrated special hardware such as stereo cameras, laser scanners, etc. are used to infer the 3D model of the distorted image which is used to remove the distortion. Recent methods focus on creating a 3D shape model based on the 2D document image. The performance of these methods is highly dependent on estimating an accurate 2D distortion grid. In the domain of printed document images, the white space between the text lines carries as much information about the 2D distortion as the text lines themselves. Based on this intuitive idea, we build a 2D distortion grid from white space lines, which can be used to rectify a printed document image by a Dewar ping algorithm. These white space lines are extracted using a propagation technique on the distance transform of the binarized document image, guided by an open active contour algorithm. We compare our proposed method against a state-of-the-art 2D distortion grid construction method and obtain better results. We also present qualitative and quantitative evaluations for the proposed method.

we propose in this paper, the use of the Contourlet Transform for evaluating the quality of the degraded historical document. To facilitate the binarization, we first improve the quality of the document image by applying the Contourlet Transform, in order to select significant coefficients. After reconstruction, a local thresholding method is used for extracting the foreground text. The proposed method is evaluated on the benchmarking dataset used in the international document image binarization contest (DIBCO 2009/2011 and H-DIBCO 2010/2012) according to the type of degradation. Promising results are obtained comparatively to the standard methods.

This paper presents a new color document image binarization that is suitable for palm leaf manuscripts and color document images. The proposed method consists of two steps: a pre-processing procedure using low-pass Wiener filter, and contrast adaptive binarization for segmentation of text from the background. Firstly, in the pre-processing stage, low-pass Wiener filter is used to eliminate noisy areas, smoothing of background texture as well as contrast enhancement between background and text areas. Finally, binarization is performed by using contrast adaptive binarization method in order to extract useful text information from low quality document images.The techniques are tested on a set of palm leaf manuscript images/color document images. The performance of the algorithm is demonstrated on by palm leaf manuscripts/color documents distorted with show-through effects, uneven background color and localized spot.