Search

In this paper, a superpixel based segmentation of Historical Document Images (HDIs) using multiscale texture analysis is proposed. A Simple Linear Iterative Clustering (SLIC) superpixel technique and Kmeans classifier are applied in order to separate the input image into background and foreground superpixels. The foreground superpixels are characterized by the standard deviation and the mean of the Gabor features. These features are extracted in a multiscale fashion to adapt to the variability of the textures that may be present in HDIs. Text/graphic separation is then performed by applying a classification of the foreground superpixels for each texture analysis scale followed by a merging step of the obtained classification results. Since the classification results depend on the used classifier, a comparative study is performed for supervised (Support Vector Machine (SVM), K-Nearest Neighbors (KNN)) and unsupervised (Kmeans, Fuzzy C-Means (FCM)) techniques. Experiments show the effectiveness of our proposed method especially when compared with similar work in the literature.

In recent decades, detection or segmentation has been one of the major interesting research subjects due to the analysis of the information. However, most of the historical document has degraded and low contrast problem. Recently, many binarization methods were proposed in order to segment the text region from the background region in the low-quality image. In this paper, an improved binarization method was inspired by Niblack method was presented. The modification focuses to find the optimum threshold value by using the Maximum-Minimum intensity technique. The main target is to reduce the unwanted detection image and increase the resultant performance compared to the original Niblack method. The proposed method was applied to the document images from H-DIBCO 2012 and H-DIBCO 2014 dataset. The results of the numerical simulation indicate that the target was achieved by the F-Measure by F-measure (58.706), PSNR (10.778) and Accuracy (86.876). This finding will give a new benchmark to other researchers to propose an advance binarization method.

Previous surveys based on historical documents on the price of slaves from Africa have contributedgreatly to accounting literature. However, most of these studies usually focus on the sale price of slaves in the colonies or on slave purchase prices in Africa. Therefore, no work has been observed in the literature relating to the effective or estimated unit cost of slaves, taking into account the total cost of all phases of the slave trade. This study aims to bring to the literature of accounting history an approach on the estimated unit cost of slaves basedon estimated total cost of all costing phases of captive transportation from Angola to Pernambuco. This approach was found in a historical document dated November 12, 1758, written by the governor of the captaincy of Pernambuco - Luis Diogo Lobo da Silva. This document was written in fulfillment of the orders of the king of Portugal, D. José I, in order to prepare a list of ships capable of transporting slaves from Africa and the details ofnecessary provisions for the slaves, who would be sent from Angola to Pernambuco. Luis Diogo Lobo da Silva was governor of the captaincy of Pernambuco from 1756 to 1763, and he was recognized for his qualities as a good colonial administrator and for adopting good management practices in his work.

Historical documents are priceless, irreplaceable and an integral part of national and world history. Handwritten documents can be a letter, notes, journal, memoir etc. or any formally written manuscript implicating a historical event or cultural heritage. These types of documents are often fragile and degraded. They have limited timespan because of materials used, and need to be digitized, restored and preserved in digital format to ensure their longevity. In this research work, we have proposed a novel methodology using a single convolutional neural network to denoise and restore old handwritten documents. The proposed model demonstrates excellent performance in restoration and preservation of severely degraded old handwritten document images of around 70 years old.

Historical documents are important sources of information. With the information revolution and the advancement of science and technology, the digitalization of historical documents will change the protection, collection, transmission, and utilization of historical documents. However, historical documents often suffer from varying degrees of degradation, such as stains, creases, uneven illumination, and seepage of ink. Compared with the general image, the document image has many characteristics. For example, the background pixels are more concentrated than the foreground pixels, and the foreground and background pixels are relatively concentrated. Based on these problems and characteristics, this paper introduces three commonly used historical document image enhancement algorithms, and improves the Sauvola algorithm for a new historical document image enhancement algorithm that does not have to calculate a special threshold for each pixel, but uses the same threshold within a fixed area to reduce the cost of time while maintaining image quality. Experimental results prove that the improved algorithm can significantly reduce the time required while ensuring the quality of the image.

This paper presents what the Satsaṅgijīvanam, a text by Śatānanda-Muni about the life and teachings of Sahajānanda, the founder of the Swaminarayana Movement, in two different passages reports about the authorship of the Śikṣāpatrī. It would appear that Swaminarayana (the name by which the founder came to be known) wrote the Śikṣāpatrī well before Śatānanda produced the version included in the Satsaṅgijīvanam. What the Satsaṅgijīvanam tells us about the authorship and the process of transmission of the Satsaṅgijīvanam itself complicates the evaluation of the Satsaṅgijīvanam as a historical document. Yet, the fact that the text shows that Swaminarayana may not be the author of the currently known Śikṣāpatrī invites reflection about the function of texts in the traditional self-perception and in the history of the Swaminarayana Movement.

A method is proposed for recognition of uchen script Tibetan historical document using baseline information. The baseline is a significant feature of uchen script Tibetan characters, and the result of Tibetan document recognition can be improved effectively by using baseline information. Firstly, the baseline is detected accurately by the upper edge of character strokes in the document. Secondly, the baseline is used for segmentation of text line and character, and the text line adhesion can be handled also. Finally, the character part above baseline and that below baseline are recognized individually, and the final results are synthesized. The experiment shows that the proposed method is effective for the recognition of Tibetan historical document, and the recognition accuracy is better than that of the whole character recognition.

The first step of historical document image recognition is the image binarization, however historical documents of poor quality, and there are all kinds of ink, stained and the background texture complexity, which brings huge challenge to the work. This paper proposes a novel binarization method for degraded historical document image based on contrast and location information of edge. Firstly, based on the fact that all pixels in a single edge are connected, a new text edge extraction method is proposed. The method combines the high and low contrast information in the image, avoids the shortcomings of noise and breakage in the edge extraction, and has high accuracy. Secondly, the Sauvola algorithm is improved. In the process of local threshold calculation, the contrast information of the edge is added to improve the adaptability of the algorithm to the brightness change and get more accurate local threshold. Finally, the binarization of image is carried out by using the local threshold and edge location information. The comprehensive experimental results on DIBCO database show that the proposed method can eliminate noise while preserving low contrast foreground, and performs better than the classical methods.

The increasing need for ontologies with practical results and the difficulties of manual construction guide us towards methods that propose automatic and semi-automated techniques for creating ontologies. The article presents a conceptual method for building ontology for historical documents aiming to support historians and researchers to organize metadata, search for relevant factors, extract information and derive new knowledge for localized metadata from documents.We envision its use for educational purposes and for the benefit of the community through several aspects, such as scientific utility, accessibility to documents from the late medieval period to explore events or personal histories of 14-16 centuries.As a case study, we implemented a semi-automatic method for extracting instances from a category of Romanian documents that generate a historical ontology. The results are evaluated on the basis of the need for an automated tool comparable to those found in the literature for other languages.

When faced with legibility issues on a historical document, several approaches can be explored to recover the degraded contents, such as hyperspectral imaging, XRF scanning or X-ray tomography. Unfortunately due to the time, costs and technical skills required, these imaging techniques cannot be applied to the numerous faded/altered documents present in library collections. Hence, there is a need for a simple imaging procedure that could be applied on a large scale, in the same way libraries and archives are being digitized. The great sensitivity of modern digital camera sensors used for digitization campaigns added to the development of simple image post-treatment tools offer new potentialities regarding this issue. This paper presents a fast and low-cost methodology to archive current aspect and reveal hidden contents of documents: UV-fluorescence photography used in combination with contrast enhancement treatments (principal component analysis, color space conversion and decorrelation stretch). The efficiency of this approach is demonstrated on the fire-damaged medieval manuscripts collection from Chartres in France.

В статье рассматривается специфика дневникового жанра, выполняющего функцию исторического документа. Помимо биографических сведений о Марии Васильчиковой, наследницы аристократического рода, оказавшегося за пределами России, представлен анализ ее «Берлинского дневника» с богатой фактографией, композиционно выполненного по принципу «течение времени». Наиболее значительным эпизодом в дневнике стали события, связанные с антигитлеровским заговором., The article focuses on the specificity of the diary genre that functions as a historical document. In addition to the biographical information about Maria Vasilchikova, the heiress of an aristocratic family that found themselves outside Russia, the paper studies her «Berlin diary», full of rich factographic material, and structured in accordance with the «time flow» principle. The key episode emphasized both in the diary and the certain article regards the events related to the anti-Hitler plot., №4(32) (2019)

International audience; This competition investigates the performance of large-scale retrieval of historical document images based on writing style. Based on large image data sets provided by cultural heritage institutions and digital libraries, providing a total of 20 000 document images representing about 10 000 writers, divided in three types: writers of (i) manuscript books, (ii) letters, (iii) charters and legal documents. We focus on the task of automatic image retrieval to simulate common scenarios of humanities research, such as writer retrieval. The most teams submitted traditional methods not using deep learning techniques. The competition results show that a combination of methods is outperforming single methods. Furthermore, letters are much more difficult to retrieve than manuscripts.

Document layout analysis is the most important part of converting scanned page images into search-able full text. An intensive amount of research is going on in the field of structured and semi-structured documents (journal articles, books, magazines, invoices) but not much in historical documents. Historical document digitization is a more challenging task than regular structured documents due to poor image quality, damaged characters, big amount of textual and non-textual noise. In the scientific community, the extraneous symbols from the neighboring page are considered as textual noise, while the appearances of black borders, speckles, ruler, different types of image etc. along the border of the documents are considered as non-textual noise. Existing historical document analysis method cannot handle all of this noise which is a very strong reason of getting undesired texts as a result from the output of Optical Character Recognition (OCR) that needs to be removed afterward with a lot of extra afford. This paper presents a new perspective especially for the historical document image cleanup by detecting the page frame of the document. The goal of this method is to find actual contents area of the document and ignore noises along the page border. We use morphological transforms, the line segment detector, and geometric matching algorithm to find an ideal page frame of the document. After the implementation of page frame method, we also evaluate our approach over 16th-19th century printed historical documents. We have noticed in the result that OCR performance for the historical documents increased by 4.49% after applying our page frame detection method. In addition, we are able to increase the OCR accuracy around 6.69% for contemporary documents too.

Současné OCR systémy běžně používají rekurentní neuronové sítě, které jsou schopné zpracovat celé řádky textu. Takovéto systémy nepotřebují metody pro segmentaci znaků. Nevýhodou je potřeba velkého množství anotovaných dat. Toto může být vyřešeno pomocí generování syntetických dat. Naneštěstí takováto data nejsou příliš vhodná pro historické dokumenty, především z důvodu kvality. Tento článek prezentuje hybridní metodu pro generování trénovacích dat pro OCR systém. Nejprve jsou shromážděny obrázky jednotlivých znaků, které jsou posléze využity pro generování celých obrázků řádek. Další přínos článku je v návrhu OCR systému s využitím konvoluční neuronové sítě a sítě LSTM. Nejprve se systém natrénuje pomocí syntetických (hybridních) dat a poté je model vyladěn pomocí anotovaného korpusu. Dále je představena trénovací strategie pro dosažení nejlepších výsledků, které jsou porovnatelné se state of the art. Current optical character recognition (OCR) systems commonly make use of recurrent neural networks (RNN) that process whole text lines. Such systems avoid the task of character segmentation necessary for character-based approaches. A disadvantage of this approach is a need of a large amount of annotated data. This can be solved by using generated synthetic data instead of costly manually annotated ones. Unfortunately, such data is often not suitable for historical documents particularly for quality reasons. This work presents a hybrid approach for generating annotated data for OCR at a low cost. We first collect a small dataset of isolated characters from historical document images. Then, we generate historical looking text lines from the generated characters. Another contribution lies in the design and implementation of an OCR system based on a convolutional-LSTM network. We first pre-train this system on hybrid data. Afterwards, the network is fine-tuned with real printed text lines. We demonstrate that this training strategy is efficient for obtaining state-of-theart results. We also show that the score of the proposed systém is comparable or even better in comparison to several state-ofthe-art systems.

This paper aims to contribute to the historical unveiling of a certain set of dispositives and discourses that befell Brazilian textile factory working women who came to reside in the convents inaugurated in the last decades of the 19th century by a textile company located in the state of Minas Gerais, Brazil. By appropriating methodological contributions such as historical document analysis, we present a historically-situated analysis of the discourses and truth effects organized by the company that influenced the lives of these women, along with an articulation of gender issues and the dynamics of power relations. An analytical scheme following the writings of Michel Foucault is proposed, in order to discuss the statements and their truth effects in the factory worker’s lives, as well as to create an analytical lens through which the discussion of gender issues can take place. Our findings include the demonstration of how gender can be seen beyond a binary, sexist and biological vision, that is, close to a historical creation of power relations that still involves the female sexed body. Lastly, we also demonstrated how the gendered idea of a female factory worker is strongly built via discourse and performed routinely by the enforced compliance to gendered norms that constrain and constitute a female worker’s subjectivity.

One of the most crucial problem in document analysis and OCR pipeline is document binarization. Many traditional algorithms over the past few decades like Sauvola, Niblack, Otsu etc,. were used for binarization which gave insufficient results for historical texts with degradations. Recently many attempts have been made to solve binarization using deep learning approaches like Autoencoders, FCNs. However, these models do not generalize well to real world historical document images qualitatively. In this paper, we propose a model based on conditional GAN, well known for its high-resolution image synthesis. Here, the proposed model is used for image manipulation task which can remove different degradations in historical documents like stains, bleed-through and non-uniform shadings. The performance of the proposed model outperforms recent state-of-the-art models for document image binarization. We support our claims by benchmarking the proposed model on publicly available PHIBC 2012, DIBCO (2009-2017) and Palm Leaf datasets. The main objective of this paper is to illuminate the advantages of generative modeling and adversarial training for document image binarization in supervised setting which shows good generalization capabilities on different inter/intra class domain document images.

One of the most crucial steps of preprocessing of document images subjected to further text recognition is their binarization, which influences significantly obtained OCR results. Since for degrades images, particularly historical documents, classical global and local thresholding methods may be inappropriate, a challenging task of their binarization is still up-to-date. In the paper a novel approach to the use of Generalized Gaussian Distribution for this purpose is presented. Assuming the presence of distortions, which may be modelled using the Gaussian noise distribution, in historical document images, a significant similarity of their histograms to those obtained for binary images corrupted by Gaussian noise may be observed. Therefore, extracting the parameters of Generalized Gaussian Distribution, distortions may be modelled and removed, enhancing the quality of input data for further thresholding and text recognition. Due to relatively long processing time, its shortening using the Monte Carlo method is proposed as well. The presented algorithm has been verified using well-known DIBCO datasets leading to very promising binarization results.

Handwritten recognition is an emerging field in the pattern recognition. Extraction of Sanskrit palm manuscript is challenging task and complicated in character recognition compared to other languages. In order to extract relevant information from the manuscript images efficiently, each step of the process requires reduction of irrelevant data such as noise on the images. This paper explains the importance of preprocessing step to determine the noise reduction, binarization, optimal binarization text, and character segmentation technique for palm manuscript. The objective of this paper is to present a survey of the existing methods for character recognition on palm manuscript which have been developed recently, to handle the historical document images.

The article describes the early thematic map of the Bosnia or Đakovo and Syrmia Diocese from the year 1826 (later in text Diocese of Đakovo and Syrmia). The map is a valuable historical document that elaborates more than just ecclesiastical contents. The diocese was partly situated in the area of today’s Republic of Croatia and Republic of Serbia. It is situated in the area surrounded by the rivers Sava, Drava and the Danube which constitute the south, north and east border of the diocese, whereas the west border roughly spreads from Slavonski Brod to Donji Miholjac. Possible map originals, as well as their authors, Demetrü Görög and Joannis Lipszky, are mentioned. The text contains the historical overview of the development of the diocese. Ecclesiastical, secular and natural contents of the map are elaborated in detail. The legend is also translated and tabular views are given about the different religions of the area.

In Mongolian historical document recognition, preprocessing mainly involves image binarization and denoising. This is a challenging task and greatly effects the accuracy of the recognition result. Concerning the fact that image binarization and denoising are both image-to-image tasks, this paper proposes an end-to-end preprocessor for Mongolian historical document OCR. The preprocessor is trained in an adversarial learning fashion and deal with binarization and denoising simultaneously. The input of the preprocessor is the color image of Mongolian document images, and the output is the clean binary images which can be used for word recognition. The preprocessor was trained on a limited dataset and performed better than the combination of binarization and denoising methods used in earlier Mongolian historical document OCR systems.

This work aims at data preparation for OCR systems based on recurrent neural networks. Precisely annotated data are necessary for training a network as well as for evaluation of OCR methods. It is possible to synthesize the data, however such data are not that realistic as the real ones. Manual annotation is thus still needed in many cases, especially in the case of historical documents we are focusing on. Although there are several complex systems for historical document processing, to the best of our knowledge, a simple annotation tool for OCR data is completely missing. Therefore, we propose and implement a set of tools utilizing artificial intelligence that simplify the annotation process. These tools create ground truths for line images that are used for training of nowadays OCR systems. Another contribution of this paper is making these tools freely available for research purposes.

In this paper, we propose a novel two-step approach, called KFBin, for the binarization of document images based on the Kalman filtering (KF) technique. In the first step, a state space model is developed as a new document image representation, and then the Kalman filter is applied to track the positions of the foreground and background information and generate two corresponding outputs, which allows the enhancement of the foreground content leading to better legibility of text. Standard thresholding algorithms were used in the second step to generate binary images from the enhanced foreground components. The performance of the proposed approach is validated on a well-known dataset and evaluated using common image binarization quality metrics. Outstanding improvement of the binarization performances of several state-of-the-art binarization methods has been achieved by using the proposed approach. Experimental results point that the poor binarization results of egraded document images can be greatly improved by enhancing their quality.

Detecting characters from historical documents is a challenging problem due to the cursive and connected characters. It is a fundamental task for recognizing historical documents. In this paper, we propose a two-dimensional context box proposal network. The network has three parts: feature extraction, two-dimensional context, and box proposal regression. For feature extraction, we employ VGG16 to extract features from an input image. Then, the extracted features are processed by two-dimensional context. We employ two Bidirectional Long Short Term Memory (BLSTM) to explore vertical and horizontal meaningful context. Finally, the bounding box is predicted from the output of the two-dimensional context. We tested our proposed system on 28 books of Kuzushiji documents. The results of the experiments show the effectiveness of our proposed two-dimensional context for character detection. Our system achieved 88.50% and 92.46% of F1 score on validation and testing sets, respectively, which outperforms the baseline system (Connectionist Text Proposal Network).

Automatic analysis of scanned historical documents comprises a wide range of image analysis tasks, which are often challenging for machine learning due to a lack of human-annotated learning samples. With the advent of deep neural networks, a promising way to cope with the lack of training data is to pre-train models on images from a different domain and then fine-tune them on historical documents. In the current research, a typical example of such cross-domain transfer learning is the use of neural networks that have been pre-trained on the ImageNet database for object recognition. It remains a mostly open question whether or not this pre-training helps to analyse historical documents, which have fundamentally different image properties when compared with ImageNet. In this paper, we present a comprehensive empirical survey on the effect of ImageNet pre-training for diverse historical document analysis tasks, including character recognition, style classification, manuscript dating, semantic segmentation, and content-based retrieval. While we obtain mixed results for semantic segmentation at pixel-level, we observe a clear trend across different network architectures that ImageNet pre-training has a positive effect on classification as well as content-based retrieval.

In this article, I seek to define the status and role of Thomas Paine’s Common Sense as a historical document. I argue that although Paine’s influential pamphlet offers no original ideas and seems simply to reinforce existing trends, its layered text transcends the regurgitation of propaganda and extends to literary achievement in its reflection of social and economic conditions, its deliberate narrative style, and its usage of literary devices and culture references grounded in historical context. Consequently, my methodology is necessarily focused through literary discourse to achieve historical understanding of this key document from the American Revolution.

Information acquisition from degraded historical document has always been a challenging task due to various forms of degradation. Image binarization is very much essential in the restoration of degraded historical documents. Eventhough many algorithms have been proposed, still there is a need for an effective algorithm to solve all kind of degradation problems. In this paper ,an optimum binarization technique is proposed that addresses these issues by using a combined approach of local image contrast and gradient . Firstly,the input image is binarized and then canny egde map is applied to extract text stroke edge pixels.To enhance further,morphological operations are carried out based on shapes.Finally an adaptive thresholding is applied to segment foreground and background pixels.To determine the quality, the proposed method has been tested on 3 public data sets (DIBCO 2009, 2010, 2011) that were taken from pattern recognition and image analysis(PRImA) research lab. Simulation result shows that the proposed binarization method achieves performance improvement interms of F-measure, NRM, MPM, PSNR as 88.4461, 0.0708, 0.00265 and 18.420 respectively.

Writer identification is one of the research hotspots of computer vision and pattern recognition, and it is of great significance in the fields of judicial authentication, file security protection, historical document analysis, and so on. However, many problems are still challenging due to the different writing sources, the common features of learning local features, and the implicit features of handwriting style. This paper uses the fusion of depth features and manual features to obtain handwriting style features from handwriting pictures. Firstly, the handwriting picture is pre-treatment and divided into small pixel blocks, and then the depth feature and LPQ feature information are extracted from each pixel block, and the depth features are reduced by PCA, and then the local features are encoded into global features through the Vlad algorithm. So far, the depth global feature and the LPQ global feature of a page of handwriting pictures are obtained, and the two features are combined as the global feature vector of the page of handwriting. And our method has achieved good results on the CASIA-HWDB data set.

This paper introduces a novel deep learning architecture, named DIGITNET, and a large-scale digit dataset, named DIDA, to detect and recognize handwritten digits in historical document images written in the nineteen century. To generate the DIDA dataset, digit images are collected from 100,000 Swedish handwritten historical document images, which were written by different priests with different handwriting styles. This dataset contains three sub-datasets including single digit, large-scale bounding box annotated multi-digit, and digit string with 250,000, 25,000, and 200,000 samples in Red-Green-Blue (RGB) color spaces, respectively. Moreover, DIDA is used to train the DIGITNET network, which consists of two deep learning architectures, called DIGITNET-dect and DIGITNET-rec, respectively, to isolate digits and recognize digit strings in historical handwritten documents. In DIGITNET-dect architecture, to extract features from digits, three residual units where each residual unit has three convolution neural network structures are used and then a detection strategy based on You Look Only Once (YOLO) algorithm is employed to detect handwritten digits at two different scales. In DIGITNET-rec, the detected isolated digits are passed through 3 different designed Convolutional Neural Network (CNN) architectures and then the classification results of three different CNNs are combined using a voting scheme to recognize digit strings. The proposed model is also trained with various existing handwritten digit datasets and then validated over historical handwritten digit strings. The experimental results show that the proposed architecture trained with DIDA (publicly available from: https://didadataset.github.io/DIDA/) outperforms the state-of-the-art methods. © 2020 The Author(s) open access Scalable resource efficient systems for big data analytics

Martin Waldseemuller’s 1507 world map has been on prominent display at the Library of Congress in Washington, DC, since 2007. As a historical document it owes its unusually high level of familiarit...

Dina Pronicheva was one of the few survivors of the massacre at Babi Yar in September 1941. In April 1968, she gave her testimony before the Darmstadt Federal State Court at the trial of Kuno Friedrich Callsen and nine other former members of the Sonderkommando no. 4a, who were accused of committing murder and of being an accessory to murder. Dina Pronicheva’s statement is a key historical document with regard to the atrocity that occurred at Babi Yar.

Educar en la creatividad es educar para el cambio y formar personas capaces para ser originales, flexibles, con visión futura, iniciativa, confianza, amantes de los riesgos y prestas para afrontar los obstáculos y problemas que se les van presentado en su vida escolar y cotidiana, además, de ofrecerles herramientas para la innovación. La creatividad puede ser desarrollada a través del proceso educativo, favoreciendo potencialidades y consiguiendo una mejor utilización de los recursos individuales y grupales dentro del proceso de enseñanza-aprendizaje, y esta llega a su alcance máximo a partir de cada una de las técnicas que el docente sea capaz de aplicar para el desarrollo de los objetivos propuestos en cada clase. El objetivo fundamental de esta investigación es describir algunas de las técnicas de estudio en la Educación Superior, que aún son insuficiente en su aplicación práctica educacional para la mejora del proceso enseñanza aprendizaje de las Universidades. Los métodos fundamentales utilizados fueron, del nivel teórico el analítico sintético y el histórico lógico y del nivel empírico el análisis de documentos. Los resultados fundamentales fueron describir las técnicas de estudio que se desarrollan el campo del conocimiento creativo, lo que posibilita, el desarrollo del conocimiento en todos los ámbitos de la actividad humana y es el producto de un devenir histórico social determinado, estas se aplican en dependencia del contexto, el sujeto, los objetivos propuestos, e influyen a su vez en estos y cada uno de los cambios sociales que trasciende a lo largo de la formación del ser humano. Se puede concluir que se han descrito técnicas de estudios que provocan la creatividad en el proceso de enseñanza aprendizaje de las universidades.

This study demonstrates how the cultural role of Ottoman women began to change during the nineteenth and twentieth centuries as well as considering emerging conflicts due to their altering roles in society as they were educated in the Darulmuallimat (teachers’ college for women) and acquired social positions as woman instructors. The first phase of the study is about schooling for women in the late Ottoman Empire and how women became teachers. The work mentions an interesting historical document which shows the relationship between a female instructor and a director of education (maarif muduru) in Trabzon. This document also points to the disturbances aroused by these changes in women’s social status which needed to be reconstructed. It indicates how the government took measures to preserve the existing norms as women became more visible in the community and reminded them that their first responsibility was always about preserving their chastity and esteem. The first woman teachers to commence par...

The Image-based historical document dating problem is studied.We use the informative and meaningful junction patterns to represent handwriting styles.A temporal pattern codebook is obtained to discover the evolution of handwritten patterns over time. Manuscript dating is an essential part of historical scholarship. This paper proposes a framework for image-based historical manuscript dating based on handwritten pattern analysis in scanned historical manuscript images. We first use a singular structural feature to extract the mid-level handwritten patterns in historical document images and then encode the discovered handwritten patterns based on a codebook which contains the temporal information. We evaluate our method on the Medieval Paleographic Scale (MPS) data set and experimental results demonstrate that the feature representation based on the codebook which contains temporal information is more discriminative and powerful for dating. In addition, our proposed method can also visualize the evolution of handwritten patterns over time.

It is of essential importance for historians to know the date and place of origin of the documents they study. It would be a huge advancement for historical scholars if it would be possible to automatically estimate the geographical and temporal provenance of a handwritten document by inferring them from the handwriting style of such a document. We propose a multiple-label guided clustering algorithm to discover the correlations between the concrete low-level visual elements in historical documents and abstract labels, such as date and location. Firstly, a novel descriptor, called Histogram of Orientations of Handwritten Strokes (HOHS or H2OS), is proposed to extract and describe the visual elements, which is built on a scale-invariant polar-feature space. In addition, the Multi- Label Self-Organizing Map (MLSOM) is proposed to discover the correlations between the low-level visual elements and their labels in a single framework. Our proposed MLSOM can be used to predict the labels directly. Moreover, the MLSOM can also be considered as a pre-structured clustering method to build a codebook, which contains more discriminative information on date and geography. Experimental results on the Medieval Paleographic Scale (MPS) data set demonstrate that our method achieves state-of-the-art results.

Despite all the technological developments in image acquisition and processing, preserving old documents and other data of historical interest is still a very challenging issue. Indeed, these documents are often proned to several types of artifacts affecting their readability. Furthermore, due to the considerable information considered in such media, reducing the size of the digitized documents is another challenging problem since their entropy is often high due to the presence of artifacts. Thus, we believe that directing the lost of information onto artifacts could bring an elegant solution to this issue. In this paper, we propose the first approach joining enhancement-compression for handwritten document images. This approach presents a novel foreground/background segmentation algorithm, using both directional and contrast features to highlight the original information. This pre-treatment step is embedded into DjVu encoder, which is commonly used in National Archives and libraries frameworks, to drive the compression rate. Both objective evaluation and perceptual judgment demonstrate the efficiency of the proposed scheme on the whole DIBCO datasets.

Historical manuscript dating has always been an important challenge for historians but since countless manuscripts have become digitally available recently, the pattern recognition community has started addressing the dating problem as well. In this paper, we present a family of local contour fragments (kCF) and stroke fragments (kSF) features and study their application to historical document dating. kCF are formed by a number of k primary contour fragments segmented from the connected component contours of handwritten texts and kSF are formed by a segment of length k of a stroke fragment graph. The kCF and kSF are described by scale and rotation invariant descriptors and encoded into trained codebooks inspired by classical bag of words model. We evaluate our methods on the Medieval Paleographical Scale (MPS) data set and perform dating by writer identification and classification. As far as dating by writer identification is concerned, we arrive at the conclusion that features which perform well for writer identification are not necessarily suitable for historical document dating. Experimental results of dating by classification demonstrate that a combination of kCF and kSF achieves optimal results, with a mean absolute error of 14.9 years when excluding writer duplicates in training and 7.9 years when including writer duplicates in training.

A mud rain event is observed in February, 1882 across a wide area of Japan's main island. Records and articles in several newspapers that written at Kyoto, Mie, Gifu, Aichi, Nagano, Tokyo, Chiba, Ibaraki Prefectures and so on, are transcribed to characterize the mud rain event. The records mostly described that something like ash, sand or mud fallen and accumulated. One article described that the night is like the one without moon. Although there was a rumor that the mud rain is caused by a volcano eruption, volcano eruption is not officially reported in the period. The point of observation seems to migrate from west to east in three days. The mud rain estimated to be brought by (1) ash fall from a volcano eruption, (2) Asian dust, or (3) local dust storm.

Previous studies of Champa history mainly based on an assumption that Champa was an “Indianized” kingdom who profoundly influenced by Indian civilization. Recent studies, however, have convinced that apart from Indian influence, Champa did benefit greatly from other civilization centers, especially China and Middle East. This article, relies on Chinese historical document and the old inscriptions of ancient Champa as well as recent archaeological findings in central Vietnam, aims to shed new light on the diplomatic relations and commercial links between Champa with China and Middle East during the period from the 7th to the 10th: Firstly, the tributary trade and diplomacy from Champa to Chinese courts will be taken into account; and secondly, the engagement of Champa in the expansion of Muslim trade network in the Indian Ocean will be examined. Les études antérieures sur l’histoire du Champa sont principalement basées sur l’hypothèse que le Champa était un royaume « indianisé », profondément influencé par la civilisation indienne. Des études récentes, cependant, ont démontré qu’en dehors de l’influence indienne, le Champa a également fortement bénéficié de l’influence d’autres civilisations, en particulier la Chine et le Moyen-Orient. Cet article, qui se fonde sur un document historique chinois, sur les anciennes inscriptions de l’ancien Champa, ainsi que sur les récentes découvertes archéologiques dans le centre du Vietnam, vise à apporter un nouvel éclairage sur les relations diplomatiques et des liens commerciaux entre le Champa et la Chine et le Moyen-Orient au cours de la période allant du viie au xe siècle. Dans un premier temps seront examinés le commerce et la diplomatie du Champa tributaires des tribunaux chinois ; dans un second temps, l’engagement du Champa dans l’expansion du réseau commercial musulman dans l’océan Indien sera examinée.

On 18 December 1867 a disastrous earthquake struck off northern Taiwan and generated a tsunami that caused hundreds of deaths. At that time, with little information available, people could not be expected to identify the mechanism of the1867 Keelung earthquake or the subsequent tsunami. To reconstruct the earthquake and tsunami available historical documents and references were reviewed and verified. The data were then evaluated for its’ credibility. The historical place names were correlated with the present locations and GIS tools were used to reconstruct the earthquake and tsunami and identify the distribution of the resulting damage. Excluding the damage recorded in the Keelung area, there is evidence that shows that the 1867 Keelung earthquake and tsunami killed more than 580 people. The coastal area from Jinshan to Keelung Harbor was the main affected area. With a recorded tsunami wave height of 6 m occurring in Huanggang and Shueiwei, the run-up height in Jinbaoli Old Street and the Badouzi area is estimated to have been 15 m high. The tsunami wave height was observed to be 205 cm at Keelung Harbor Bay. The attenuation law was adopted to simulate the earthquake intensity distribution. The source parameters reasonableness and validity were considered by comparing the earthquake intensity distribution and the resulting damage. Our results show that the 1867 Keelung earthquake was highly correlated with the offshore Shanchiao Fault extension. The length the fault is about 40 km, with the epicenter located at 25.34°N, 121.91°E and focal depth of 10 km. The moment magnitude was 7.0.

This paper presents a new lexicon reduction method for historical Arabic scripts that compares the input subword image with the lexicon entries, and selects the most similar ones. In comparing two subword images, more importance is given to the prominent shape regions, defined as those local regions of a subword that distinguish it from other lexicon subwords. In this method, first a retrieval-based measure is applied to compute a distinction score for each local region, indicating how prominent that region is. These scores are subsequently used in a proposed distance measure to modulate the weights of corresponding shape features, where most distinctive regions are given more weight. A global shape-based lexicon reduction based on the characteristic loci is used as well, to complement the local subword descriptors. We evaluated the performance of our proposed method on the Ibn Sina database, containing more than 12,000 subwords extracted from a historical Arabic document, and the degree of reduction of 98.15 % with an accuracy of 90.15 % was achieved.

Esta investigación presenta los aportes pedagógicos, investigativos y de patrimonio histórico cultural en la Escuela Normal, para la creación, desarrollo y promoción de Institutos que prolongaron su influencia en el período de 1936 a 1951. El trabajo, se enmarca en la revisión histórico documental con la historia social y de las instituciones educativas con fuentes primarias y secundarias de archivos encontrados en Tunja y Bogotá, entre ellos: el Archivo General de la Nación y Archivo Histórico de la UPTC. En este contexto, la pregunta que guió la investigación se relacionó con ¿Cuáles fueron los aportes pedagógicos, investigativos y de patrimonio histórico cultural de la Escuela Normal Superior, para la creación, desarrollo y promoción de Institutos que prolongaron su influencia educativa en Colombia? Se concluye que la Escuela Normal Superior asumió los modelos provenientes del humanismo y la ciencia, es decir, la ciencia asociada a la enseñanza y los saberes para la vida para construir su propio modelo pedagógico de manera ecléctica, que incidieron en la formación de un maestro formado en un saber específico capaz de enfrentar el campo de la pedagogía, la investigación y la alta cultura en su quehacer diario, aspectos reflejados en las licenciaturas e institutos anexos, quienes prolongaron su influencia educativa y existencia para la construcción de la nación colombiana de mediados de siglo XX.

This article examines some recent deliberations over the application of historical-critical methods to the Qurʼān in Lebanon, mainly based on two examples: the debate over the Arabic translation by George Tamer of Theodor Noldeke’s History of the Qur’ān; and the contestations to historicizing approaches of Shi’ite Shaykh Shafīq Jarādī, director of the Sapiential Knowledge Institute, who has approached questions over hermeneutics and the history of the Qurʼān from the angle of Islamic (Ṣadrian) philosophy. Examination of Jarādī’s work suggests that understanding the Qurʼān as a literary or historical document presupposes not only a change in epistemology or method, but depends on how human nature and language are conceptualized. Based on these examples, the article explores the political and epistemological rationalities the critics and proponents of the historical-critical approach to the Qurʼān employ in their discussions. The article argues that methodological, historical, and hermeneutical disc...

Research in document work has tended to take a sociocultural perspective. Recent interest in document experience invites the consideration of document work from the perspective of an individual's lived experience. This paper reports on a holistic, single-case study of how the head gardener at Shofuso Japanese House and Garden, a historic landscape site in Philadelphia, experiences the document work involved in developing a comprehensive garden plan. A hermeneutic analysis of the data reveals how the underlying foundational values of authenticity, education and reducing ambiguity support the process of document work in this case, which involves summoning diverse knowledge, channeling the master and stepping back. This process is punctuated by organizational and historical challenges. These findings suggest that the theoretical framework of foundation-process-challenges may be used to study the lived experience of document work in other cases. Further ramifications are discussed for practice in gardening and historical document work.

A Nom historical document recognition system is being developed for digital archiving that uses image binarization, character segmentation, and character recognition. It incorporates two versions of off-line character recognition: one for automatic recognition of scanned and segmented character patterns (7660 categories) and the other for user handwritten input (32,695 categories). This separation is used since including less frequently appearing categories in automatic recognition increases the misrecognition rate without reliable statistics on the Nom language. Moreover, a user must be able to check the results and identify the correct categories from an extended set of categories, and a user can input characters by hand. Both versions use the same recognition method, but they are trained using different sets of training patterns. Recursive X---Y cut and Voronoi diagrams are used for segmentation; k---d tree and generalized learning vector quantization are used for coarse classification; and the modified quadratic discriminant function is used for fine classification. The system provides an interface through which a user can check the results, change binarization methods, rectify segmentation, and input correct character categories by hand. Evaluation done using a limited number of Nom historical documents after providing ground truths for them showed that the two stages of recognition along with user checking and correction improved the recognition results significantly.

Timothy Geithner's memoir of the financial crisis of 2007–08—Stress Test: Reflections on Financial Crises—is an important historical document offering details of how policies were formed and implemented during the crisis, showing the political constraints, and offering lessons for future crises. Walter Bagehot's classic rule for fighting crises— that the central bank should lend against good collateral at a high rate—is passive and incomplete. Geithner argues for the use of overwhelming force to reestablish confidence. Also, although the Federal Reserve's new crisis lending programs needed to be anonymous so as not to reveal weak banks' identities—“stigma”—the stress tests during the crisis did reveal information that may have been useful in reestablishing confidence. (JEL B31, E44, E63, G01, G21, G28)

This paper makes an attempt to call attention and point to the importance of Manchu historical records, but at the same time warns against the pitfalls of uncritical utilisation of these historical sources (the possibility of falsification and the fabrication of historical material). The authors focus on volume 20 of the 親征平定朔漠方略 Qinzhengpingdingshuo-mofanglue (Beye dailame wargi amargi babe necihiyeme toktobuha bodogon i bithe. orici debtelin) written in Manchu. This Manchu historical document is of prime importance in the historical enquiry of the period. It gives a clear picture of the military strategy of the time and provides accurate facts concerning the exact names of persons and places, the system of administration, wartime munitions mobilisation, and much more.

Nowadays, deep learning methods are employed in a broad range of research fields. The analysis and recognition of historical documents, as we survey in this work, is not an exception. Our study analyzes the papers published in the last few years on this topic from different perspectives: we first provide a pragmatic definition of historical documents from the point of view of the research in the area, then we look at the various sub-tasks addressed in this research. Guided by these tasks, we go through the different input-output relations that are expected from the used deep learning approaches and therefore we accordingly describe the most used models. We also discuss research datasets published in the field and their applications. This analysis shows that the latest research is a leap forward since it is not the simple use of recently proposed algorithms to previous problems, but novel tasks and novel applications of state of the art methods are now considered. Rather than just providing a conclusive picture of the current research in the topic we lastly suggest some potential future trends that can represent a stimulus for innovative research directions.

In this paper, we tackle the problem of categorizing and identifying cross-depicted historical motifs using recent deep learning techniques, with aim of developing a content-based image retrieval system. As cross-depiction, we understand the problem that the same object can be represented (depicted) in various ways. The objects of interest in this research are watermarks, which are crucial for dating manuscripts. For watermarks, cross-depiction arises due to two reasons: (i) there are many similar representations of the same motif, and (ii) there are several ways of capturing the watermarks, i.e., as the watermarks are not visible on a scan or photograph, the watermarks are typically retrieved via hand tracing, rubbing, or special photographic techniques. This leads to different representations of the same (or similar) objects, making it hard for pattern recognition methods to recognize the watermarks. While this is a simple problem for human experts, computer vision techniques have problems generalizing from the various depiction possibilities. In this paper, we present a study where we use deep neural networks for categorization of watermarks with varying levels of detail. The macro-averaged F1-score on an imbalanced 12 category classification task is 88.3 %, the multi-labelling performance (Jaccard Index) on a 622 label task is 79.5 %. To analyze the usefulness of an image-based system for assisting humanities scholars in cataloguing manuscripts, we also measure the performance of similarity matching on expert-crafted test sets of varying sizes (50 and 1000 watermark samples). A significant outcome is that all relevant results belonging to the same super-class are found by our system (Mean Average Precision of 100%), despite the cross-depicted nature of the motifs. This result has not been achieved in the literature so far.

Image binarization is one of the key operations decreasing the amount of information used in further analysis of image data, significantly influencing the final results. Although in some applications, where well illuminated images may be easily captured, ensuring a high contrast, even a simple global thresholding may be sufficient, there are some more challenging solutions, e.g., based on the analysis of natural images or assuming the presence of some quality degradations, such as in historical document images. Considering the variety of image binarization methods, as well as their different applications and types of images, one cannot expect a single universal thresholding method that would be the best solution for all images. Nevertheless, since one of the most common operations preceded by the binarization is the Optical Character Recognition (OCR), which may also be applied for non-uniformly illuminated images captured by camera sensors mounted in mobile phones, the development of even better binarization methods in view of the maximization of the OCR accuracy is still expected. Therefore, in this paper, the idea of the use of robust combined measures is presented, making it possible to bring together the advantages of various methods, including some recently proposed approaches based on entropy filtering and a multi-layered stack of regions. The experimental results, obtained for a dataset of 176 non-uniformly illuminated document images, referred to as the WEZUT OCR Dataset, confirm the validity and usefulness of the proposed approach, leading to a significant increase of the recognition accuracy.