Degraded document image binarization using structural symmetry of strokes

In this era of digitization, most hardcopy documents are being transformed into digital formats. In the process of transformation, large quantities of documents are stored and preserved through electronic scanning. These documents are available from various sources such as ancient documentation, old legal records, medical reports, music scores, palm leaf, and reports on security-related issues. In particular, ancient and historical documents are hard to read due to their degradation in terms of low contrast and existence of corrupted artefacts. In recent times, degraded document binarization has been studied widely and several approaches were developed to deal with issues and challenges in document binarization. In this paper, a comprehensive review is conducted on the issues and challenges faced during the image binarization process, followed by insights on various methods used for image binarization. This paper also discusses the advanced methods used for the enhancement of degraded documents that improves the quality of documents during the binarization process. Further discussions are made on the effectiveness and robustness of existing methods, and there is still a scope to develop a hybrid approach that can deal with degraded document binarization more effectively.

https://www.mdpi.com/2313-433X/5/4/48/pdf

Degraded Historical Document Binarization: A Review on Issues, Challenges, Techniques, and Future Directions.

Genetic algorithm and mathematical morphology based binarization method for strip steel defect image with non-uniform illumination

Binarization of historical documents is difficult and is still an open area of research. In this paper, a new binarization technique for document images is presented. The proposed technique is based on the most commonly used binarization method: Sauvola’s, which performs relatively well on classical documents, however, three main defects remain: the window parameter of Sauvola’s formula does not fit automatically to the image content, is not robust to low contrasts, and not invariant with respect to contrast inversion. Thus on documents such as magazines, the content may not be retrieved correctly. In this paper we use the image contrast that is defined by the local image minimum and maximum in combination with the computed Sauvola’s binarization step to guarantee good quality binarization for both low and correctly contrasted objects inside a single document, without adjusting manually the user-defined parameters to the document content.

ISauvola: Improved Sauvola’s Algorithm for Document Image Binarization

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.

https://link.springer.com/content/pdf/10.1007/s42979-020-00176-1.pdf

Historical Document Image Binarization: A Review

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.

A new efficient binarization method: application to degraded historical document images

Old document images often suffer from different types of degradation that render their binarization a challenging task. In this paper, a new binarization algorithm for degraded document images is presented. The method is based on active contours evolving according to intrinsic geometric measures of the document image, Nib lack's thresholding is also used to control the active contours propagation. The validity of the proposed method is demonstrated on both recent and historical document images including different types of degradations, the results are compared with a number of known techniques in the literature.

An Active Contour Based Method for Image Binarization: Application to Degraded Historical Document Images

Text line segmentation in handwritten documents is an important step in many high level processing such as handwritten document enhancement and text recognition. In this paper we describe a novel approach of text line segmentation based on tracking. In this sense, we consider each connected component in the image as a moving object in its respective line and find its best match given its history motion, i.e. the closest connected component that lie in its trajectory. Direction of motion gives direction of handwritten text and is the output of our tracking algorithm. We apply our approach to images of ICDAR 2013 handwritten segmentation contest and report an overall detection rate of \(86.51\%\).

Zineb Hadjadj

Papers

ISauvola: Improved Sauvola’s Algorithm for Document Image Binarization

A new efficient binarization method: application to degraded historical document images

An Active Contour Based Method for Image Binarization: Application to Degraded Historical Document Images

Text Line Segmentation in Handwritten Documents Based on Connected Components Trajectory Generation

A tracking approach for text line segmentation in handwritten documents