Academic literature on the topic 'Document image collections'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the lists of relevant articles, books, theses, conference reports, and other scholarly sources on the topic 'Document image collections.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Journal articles on the topic "Document image collections"
1
Han, Yuehui, Weilan Wang, Huaming Liu, and Yiqun Wang. "A Combined Approach for the Binarization of Historical Tibetan Document Images." International Journal of Pattern Recognition and Artificial Intelligence 33, no. 14 (May 9, 2019): 1954038. http://dx.doi.org/10.1142/s0218001419540387.
Full textAbstract:
It is common that historical Tibetan documents belonging to historical collections are poorly preserved and are prone to degradation processes. This causes many challenges that can be addressed by image binarization, the most common of which is stains. A lack of uniform standard datasets makes it difficult to evaluate binarization effects. Motivated by the poor effects and difficulty of evaluating the binarization of historical Tibetan document images, a combined approach is proposed that aims to improve overall performance. The method includes the following parts: first, image generation through standard binarization and the background extraction of color images, which are both used for image synthesis in preparing for an evaluation. Then, preliminary binarization processing is implemented through channel combination in the lab color space and through local binarization. The synthetic images are used to select the coefficient when the channels are combined. Furthermore, Local Binary Pattern (hereafter LBP) and image smoothing is carried out after the combination of the channels to obtain the outline of the text area. Finally, the final binarization image is obtained by combining the preliminary binarization image and the text area contour image. Our method achieved top performance compared to other methods after a large number of synthetic image tests with a variety of background types.
2
Zhang, Xiafen, and Vijayan Sugumaran. "Content Based Search Engine for Historical Calligraphy Images." International Journal of Intelligent Information Technologies 10, no. 3 (July 2014): 1–18. http://dx.doi.org/10.4018/ijiit.2014070101.
Full textAbstract:
Paper collections of historical calligraphy objects in Libraries and museums are scanned into document images to serve the academic society. However, these digitized collections are in image format, lacking the technology to search by image content. This paper proposes a search engine for searching calligraphy image content. First, 2503 page images are segmented into characters and components. Second, characters are interactively labeled and features are extracted to build a calligraphy database. When an image search query is submitted, coarse features are first extracted and used to prune the long list of calligraphy characters into a shorter list. Then fine shape features are employed to determine the most similar characters. iDistance and NB-Tree are used to create the high dimensional index. The efficiency of the algorithm has been demonstrated through experiments with 110,737 individual calligraphic character images. This research provides a demonstration of the potential use of calligraphy content search on the web.
3
Paulus, Erick, Mira Suryani, Setiawan Hadi, and Akik Hidayat. "INVESTIGASI SEGMENTASI BARIS UNTUK CITRA DOKUMEN SUNDA LAMPAU." JIKO (Jurnal Informatika dan Komputer) 2, no. 2 (October 12, 2017): 60. http://dx.doi.org/10.26798/jiko.2017.v2i2.65.
Full textAbstract:
The variety of image quality of old Sundanese documents can be a real challenge for the process of text line segmentation. This paper describes the results of the investigation of two text line segmentation methods against several collections of Sunda document images, ie projection profile method and Seam Carving method. The deep investigation is done on handwritten documents written on lontar and paper media. The comparative experimental study was used as an investigative methodology in this study. Both methods is tested their performance capability on colored images and binary images using the evaluation matrix provided in handwriting segmentation competition ICDAR 2013. Experimental results show that projection profile method can work optimally on binary image and the type of writing is relatively horizontal. While the Seam Carving method is able to segment the lines in a non-linear manner and produce performance above 80%. With the added of binarization process in the pre-processing stage, the performance of Seam Carving method can increase up to 99% and the number of segmented lines is close to the number of groundtruth lines.
4
Alturki, Hend Mohammed. "Museum Collections and the Importance of Studying History." Advances in Social Sciences Research Journal 7, no. 8 (August 12, 2020): 118–27. http://dx.doi.org/10.14738/assrj.78.8771.
Full textAbstract:
Generally speaking , museums reflect peoples civilizations, enhance patriotism , and play a vital role in serving culture and heritage .in addition, they monitor and document the history of nations and traditions of peoples through their cultural programs. They also provide an image of the cultural momentum and indicate how far the society is aware of the importance of historical documentation. From this perspective , museum visitors have the opportunity to be acknowledged with the cultures and civilizations of nations through their antiquity collections .
5
Giral, Angela. "Digital image libraries and the teaching of art and architectural history." Art Libraries Journal 23, no. 4 (1998): 18–25. http://dx.doi.org/10.1017/s0307472200011251.
Full textAbstract:
Can museums and libraries profit from sharing their information, visual or textual? Is direct access to digital archives a more logical or economic way to develop access to images for teaching and research than assembling local collections? Recent digital image library projects in the United States, and their impact on the teaching practices of art and architectural historians, show the advantages of focusing on issues such as licensing and intellectual property, metadata and evolving cataloging practice, image quality, and the different costs of creation and delivery. But there are other potential benefits such as document delivery and the dissemination of archival information, as well as the preservation of fragile illustrated texts through digital imaging.
6
Lafia, Sara, David A. Bleckley, and J. Trent Alexander. "Digitizing and parsing semi-structured historical administrative documents from the G.I. Bill mortgage guarantee program." Journal of Documentation 79, no. 7 (July 31, 2023): 225–39. http://dx.doi.org/10.1108/jd-03-2023-0055.
Full textAbstract:
PurposeMany libraries and archives maintain collections of research documents, such as administrative records, with paper-based formats that limit the documents' access to in-person use. Digitization transforms paper-based collections into more accessible and analyzable formats. As collections are digitized, there is an opportunity to incorporate deep learning techniques, such as Document Image Analysis (DIA), into workflows to increase the usability of information extracted from archival documents. This paper describes the authors' approach using digital scanning, optical character recognition (OCR) and deep learning to create a digital archive of administrative records related to the mortgage guarantee program of the Servicemen's Readjustment Act of 1944, also known as the G.I. Bill.Design/methodology/approachThe authors used a collection of 25,744 semi-structured paper-based records from the administration of G.I. Bill Mortgages from 1946 to 1954 to develop a digitization and processing workflow. These records include the name and city of the mortgagor, the amount of the mortgage, the location of the Reconstruction Finance Corporation agent, one or more identification numbers and the name and location of the bank handling the loan. The authors extracted structured information from these scanned historical records in order to create a tabular data file and link them to other authoritative individual-level data sources.FindingsThe authors compared the flexible character accuracy of five OCR methods. The authors then compared the character error rate (CER) of three text extraction approaches (regular expressions, DIA and named entity recognition (NER)). The authors were able to obtain the highest quality structured text output using DIA with the Layout Parser toolkit by post-processing with regular expressions. Through this project, the authors demonstrate how DIA can improve the digitization of administrative records to automatically produce a structured data resource for researchers and the public.Originality/valueThe authors' workflow is readily transferable to other archival digitization projects. Through the use of digital scanning, OCR and DIA processes, the authors created the first digital microdata file of administrative records related to the G.I. Bill mortgage guarantee program available to researchers and the general public. These records offer research insights into the lives of veterans who benefited from loans, the impacts on the communities built by the loans and the institutions that implemented them.
7
Gudonis, Vytautas. "THE IMAGE A VISUALLY IMPAIRED PERSON IN PHILATELY AS A MEANS OF FORMING AN ADEQUATE ATTITUDE TOWARDS THE BLINDNESS AND BLIND." SOCIETY. INTEGRATION. EDUCATION. Proceedings of the International Scientific Conference 4 (May 21, 2019): 390. http://dx.doi.org/10.17770/sie2019vol4.3962.
Full textAbstract:
The topic of blindness and the image of a blind person in philately, although rarely analysed, has a great information potential. This research topic is part of our research "The Image of a Blind Man in the Cultural Heritage of Humanity." The purpose of the study is to systematize knowledge on the subject of image and blindness in philately, to consider the social aspects of this phenomenon. To collect information, the bulletin used the analysis of literature and the search for postage stamps depicting blind people in private collections of philatelists. The iconological method of interpretation of culture and art history was also used, which permitted to reveal the meaning of visions, symbols and their contexts. The monograph is based on the methodological assumptions of art historians Aby Walburg (1866 – 1929) and Erwin Panofsky (1892 – 1968), who claimed that historical and social aspects could be revealed through the works of art. E. Panofsky states that the works of art as human signs as well as other works can be considered documents, encoding the knowledge of the epoch, its culture and attitudes. The work of art is a symbol, indicating “something else” and allowing us to perceive the allegory; it is a document, telling us about certain cultural, religious, social and historic phenomena, depending on the context. The image of a blind person in stamps and commemorative envelopes are divided according to separate themes and analysed as social phenomena. The image of the blind and the topic of blindness in philately allow acquiring more knowledge about the blind, their potential, embossed writing, specificity of their orientation and mobility and at the same time forming positive attitudes towards visually impaired people. These findings activate further research on the image of a blind person in other areas of cultural heritage.
8
Deju, Georgeta. "The Restoration of a Hunedoara Noble Family’s Library: the Kenderesi from Sălaşu de Sus." Études bibliologiques/Library Research Studies 3, no. 3 (2021): 29–50. http://dx.doi.org/10.33993/eb.2021.03.
Full textAbstract:
The Kenderesi family from Sălaşu de Sus was one of the oldest families of Hunedoara County, with roots in a well-known Romanian family Cânde, from Ţara Haţegului. In 1887, Mihály Kenderesi and his son Ernő, donated their ‘beautiful book collection’ to the Society of History and Archaeology of Hunedoara County. The information appeared in the librarian’s report for 1887 and did not specify the title or number of the books. Thus, a research project began with the aim to identify the books with the notes and signatures of Kenderesi family members, among the documents of the Deva Museum Library. The initial findings were a no. of 21 books, printed in the 16th-19th centuries. After a few years, an archived document on the donation of the books was identified listing 54 positions, representing one periodical and books, some in rare editions. A comparison between the donation list and the inventories of the Deva Museum Library, indicated a no of 15 missing books, whilst the others were identified in The Library. Considering the number of volumes, their age, topic or the notes preserved on the pages of the books, the Kenderesi family donation that entered the collections of the Deva Museum Library in 1887 is significant for the region of Hunedoara and enriches the actual image of the bibliophile heritage.
9
Petrov, Nikolai I. "Sacralization of the Portrait of the Empress Elizabeth Petrovna in the Orenburg Gubernia in the 1760s." Herald of an archivist, no. 1 (2023): 144–58. http://dx.doi.org/10.28995/2073-0101-2023-1-144-158.
Full textAbstract:
An interesting example of the Russian phenomenon of monarch sacralization is reflected in the “lowest report” (1767) sent to the Most Holy Governing Synod by the retired secretary of the Bugulma voivodeship chancellery Ivan Nikiforovich Kurcheev (see appendix). In 1762 I. N. Kurcheev was an eyewitness to a miraculous phenomenon connected with the portrait of the Russian Empress Elizabeth Petrovna: “... And from the aforesaid image of the Most Radiant Monarchess there emanated an effulgence which attained the image of the Savior stationed in my house ...” Later I. N. Kurcheev began to revere this portrait as an icon: “... I began to put candles before this image ...” This was known to the local clergy and I. N. Kurcheev himself was convinced of the permissibility of such veneration of the Empress Elizabeth’s portrait, to whose intercession he ascribed the healing of his mother, children, and ward. I. N. Kurcheev formed a local cult of the deceased Empress, convinced of her holiness and of imperishability of her “relics” (when writing of Elizabeth’s death he used the word “dormition”). This conviction was based on the connection between the icon of the Savior and the portrait of Empress Elizabeth, miraculously shown to I. N. Kurcheev. The mentioned service of supplication (moleben) to Empress Elizabeth, which was done “under the name” of her saint patroness-namesake, as she was not canonized by the Church, correlates with the image of St. Elisabeth bearing likeness of Empress Elizabeth in the original Russian worship service to Sts. Zachariah the Prophet and Elisabeth the Righteous (the 5th of September) in the late 19th century. The later archival caption of I. N. Kurcheev’s report was supplemented by a laconic note that some “stucco image” of the Empress Elizabeth was attached to the document. Apparently, this refers to the said portrait, from which, according to I. N. Kurcheev, “emanated an effulgence” in 1762. There is no any additional information on this “stucco image.” One can assume that it was a painted bas-relief plaster portrait of the Empress Elizabeth, probably similar to mid-18th century reproductions of the lead portrait of the Empress Elizabeth by B. C. Rastrelli (1743), which are now stored in the museum collections. The published document is a peculiar and striking source on the Russian tradition of monarch’s portrait sacralization. This phenomenon of Russian folk piety developed in the 19th – 20th centuries.
10
Brown, JP. "Introduction to 3D Imaging Using Photogrammetry." Biodiversity Information Science and Standards 2 (July 4, 2018): e27029. http://dx.doi.org/10.3897/biss.2.27029.
Full textAbstract:
This full day workshop will provide an introduction to 3D imaging using photogrammetry. The course is designed for museum professionals who are already familiar with using digital single lens reflex (DSLR) cameras, and want to extend their practice to 3D imaging. Photogrammetry is a low-cost-of-entry 3D imaging method which can be used to produce excellent results for many different museum specimens, and scales well. From large buildings to tiny clay molds, photogrammetry has been used to successfully model and document a very wide variety of museum material in full color and in three dimensions. The technique can also be extended to multi-spectral imaging. The workshop will be hands-on and will cover camera setup, lighting, and image processing, imaging flat and contoured specimens. We will look at working at different scales, and metric photogrammetry using Agisoft Photoscan. The course will be led by a museum professional with five years of experience of using photogrammetry to image museum collections from bivalves and taxidermy to textiles, and fossils to furniture. Due to the intensive and fast-moving nature of the workshop, participation is limited to eight people. Participants will be expected to bring a DSLR and a laptop computer to the workshop.
Dissertations / Theses on the topic "Document image collections"
1
Iscen, Ahmet. "Continuous memories for representing sets of vectors and image collections." Thesis, Rennes 1, 2017. http://www.theses.fr/2017REN1S039/document.
Full textAbstract:
Cette thèse étudie l'indexation et le mécanisme d'expansion de requête en recherche d'image. L'indexation sacrifie la qualité de la recherche pour une plus grande efficacité; l'expansion de requête prend ce compromis dans l'autre sens : il améliore la qualité de la recherche avec un coût en complexité additionnel. Nous proposons des solutions pour les deux approches qui utilisent une représentation continue d'un ensemble de vecteurs. Pour l'indexation, notre solution est basée sur le test par groupe. Chaque vecteur image est assigné à un groupe, et chaque groupe est représenté par un seul vecteur. C'est la représentation continue de l'ensemble des vecteur du groupe. L'optimisation de cette représentation pour produire un bon test d'appartenance donne une solution basée sur la pseudo-inverse de Moore-Penrose. Elle montre des performances supérieures à celles d'une somme basique des vecteurs du groupe. Nous proposons aussi une alternative suivant au plus près les vecteurs-images de la base. Elle optimise conjointement l'assignation des vecteurs images à des groupes ainsi que la représentation vectorielle de ces groupes. La deuxième partie de la thèse étudie le mécanisme d'expansion de requête au moyen d'un graphe pondéré représentant les vecteurs images. Cela permet de retrouver des images similaires le long d'une même variété géométrique, mais éloignées en distance Euclidienne. Nous donnons une implémentation ultra-rapide de ce mécanisme en créant des représentations vectorielles incorporant la diffusion. Ainsi, le mécanisme d'expansion se réduit à un simple produit scalaire entre les représentations vectorielles lors de la requête. Les deux parties de la thèse fournissent une analyse théorique et un travail expérimental approfondi utilisant les protocoles et les jeux de données standards en recherche d'images. Les méthodes proposées ont des performances supérieures à l'état de l'artIn this thesis, we study the indexing and query expansion problems in image retrieval. The former sacrifices the accuracy for efficiency, whereas the latter takes the opposite perspective and improves accuracy with additional cost. Our proposed solutions to both problems consist of utilizing continuous representations of a set of vectors. We turn our attention to indexing first, and follow the group testing scheme. We assign each dataset vector to a group, and represent each group with a single vector representation. We propose memory vectors, whose solution is optimized under the membership test hypothesis. The optimal solution for this problem is based on Moore-Penrose pseudo-inverse, and shows superior performance compared to basic sum pooling. We also provide a data-driven approach optimizing the assignment and representation jointly. The second half of the transcript focuses on the query expansion problem, representing a set of vectors with weighted graphs. This allows us to retrieve objects that lie on the same manifold, but further away in Euclidean space. We improve the efficiency of our technique even further, creating high-dimensional diffusion embeddings offline, so that they can be compared with a simple dot product in the query time. For both problems, we provide thorough experiments and analysis in well-known image retrieval benchmarks and show the improvements achieved by proposed methods
2
Letessier, Pierre. "Découverte et exploitation d'objets visuels fréquents dans des collections multimédia." Thesis, Paris, ENST, 2013. http://www.theses.fr/2013ENST0014/document.
Full textAbstract:
L’objectif principal de cette thèse est la découverte d’objets visuels fréquents dans de grandes collections multimédias (images ou vidéos). Comme dans de nombreux domaines (finance, génétique, . . .), il s’agit d’extraire une connaissance de manière automatique ou semi-automatique en utilisant la fréquence d’apparition d’un objet au sein d’un corpus comme critère de pertinence. Une première contribution de la thèse est de fournir un formalisme aux problèmes de découverte et de fouille d’instances d’objets visuels fréquents. La deuxième contribution de la thèse est une méthode générique de résolution de ces deux types de problème reposant d’une part sur un processus itératif d’échantillonnage d’objets candidats et d’autre part sur une méthode efficace d’appariement d’objets rigides à large échelle. La troisième contribution de la thèse s’attache à construire une fonction de vraisemblance s’approchant au mieux de la distribution parfaite, tout en restant scalable et efficace. Les expérimentations montrent que contrairement aux méthodes de l’état de l’artnotre approche permet de découvrir efficacement des objets de très petite taille dans des millions d’images. Pour finir, plusieurs scénarios d’exploitation des graphes visuels produits par notre méthode sont proposées et expérimentés. Ceci inclut la détection d’évènements médiatiques transmédias et la suggestion de requêtes visuellesThe main goal of this thesis is to discover frequent visual objects in large multimedia collections. As in many areas (finance, genetics, . . .), it consists in extracting a knowledge, using the occurence frequency of an object in a collection as a relevance criterion. A first contribution is to provide a formalism to the problems of mining and discovery of frequent visual objects. The second contribution is a generic method to solve these two problems, based on an iterative sampling process, and on an efficient and scalable rigid objects matching. The third contribution of this work focuses on building a likelihood function close to the perfect distribution. Experiments show that contrary to state-of-the-art methods, our approach allows to discover efficiently very small objects in several millions images. Finally, several applications are presented, including trademark logos discovery, transmedia events detection or visual-based query suggestion
3
Diaz, Mauricio. "Analyse de l'illumination et des propriétés de réflectance en utilisant des collections d'images." Thesis, Grenoble, 2011. http://www.theses.fr/2011GRENM051/document.
Full textAbstract:
L'utilisation de collections d'images pour les applications de vision par ordinateur devient de plus en plus commune des nos jours. L'objectif principal de cette thèse est d'exploiter et d'extraire des informations importantes d'images de scènes d'extérieur a partir de ce type de collections : l'illumination présente au moment de la prise, les propriétés de reflectance des matériaux composant les objets dans la scène et les propriétés radiométriques des appareils photo utilisés. Pour atteindre notre objectif, cette thèse est composée de deux parties principales. Dans un premier temps nous allons réaliser une analyse de différentes représentations du ciel et une comparaison des images basée sur l'apparence de celui-ci. Une grande partie de l'information visuelle perçue dans les images d'extérieures est due a l'illumination en provenance du ciel. Ce facteur est représenté par les rayons du soleil réfléchis et réfractés dans l'atmosphère en créant une illumination globale de l'environnement. En même temps cet environnement détermine la façon de percevoir les objets du monde réel. Etant donné l'importance du ciel comme source d'illumination, nous formulons un processus générique en trois temps, segmentation, modélisation et comparaison des pixels du ciel, pour trouver des images similaires en se basant sur leurs apparences. Différentes méthodes sont adoptées dans les phases de modélisation et de comparaison. La performance des algorithmes est validée en trouvant des images similaires dans de grandes collections de photos. La deuxième partie de cette thèse consiste a exploiter l'information géométrique additionnelle pour en déduire les caractéristiques photométriques de la scène. A partir d'une structure 3D récupérée en utilisant des méthodes disponibles, nous analysons le processus de formation de l'image a partir de modèles simples, puis nous estimons les paramètres qui les régissent. Les collections de photos sont généralement capturées par différents appareils photos, d'où l'importance d'insister sur leur calibrage radiométrique. Notre formulation estime cet étalonnage pour tous les appareils photos en même temps, en utilisant une connaissance a priori sur l'espace des fonctions de réponse des caméras possibles. Nous proposons ensuite, un cadre d'estimation conjoint pour calculer une représentation de l'illumination globale dans chaque image, l'albedo de la surface qui compose la structure 3D et le calibrage radiométrique pour tous les appareils photosThe main objective of this thesis is to exploit the photometric information avail- able in large photo collections of outdoor scenes to infer characteristics of the illumination, the objects and the cameras. To achieve this goal two problems are addressed. In a preliminary work, we explore opti- mal representations for the sky and compare images based on its appearance. Much of the information perceived in outdoor scenes is due to the illumination coming from the sky. The solar beams are reflected and refracted in the atmosphere, creating a global illumination ambiance. In turn, this environment determines the way that we perceive objects in the real world. Given the importance of the sky as an illumination source, we formulate a generic 3–step process in order to compare images based on its appearance. These three stages are: segmentation, modeling and comparing of the sky pixels. Different approaches are adopted for the modeling and comparing phases. Performance of the algorithms is validated by finding similar images in large photo collections. A second part of the thesis aims to exploit additional geometric information in order to deduce the photometric characteristics of the scene. From a 3D structure recovered using available multi–view stereo methods, we trace back the image formation process and estimate the models for the components involved on it. Since photo collections are usually acquired with different cameras, our formulation emphasizes the estimation of the radiometric calibration for all the cameras at the same time, using a strong prior on the possible space of camera response functions. Then, in a joint estimation framework, we also propose a robust computation of the global illumination for each image, the surface albedo for the 3D structure and the radiometric calibration for all the cameras
4
Rayar, Frédéric. "Exploration interactive, incrémentale et multi-niveau de larges collections d'images." Thesis, Tours, 2016. http://www.theses.fr/2016TOUR4012/document.
Full textAbstract:
Les travaux de recherche présentés et discutés dans cette thèse s’intéressent aux grandes collections d’images numériques. Plus particulièrement, nous cherchons à donner à un utilisateur la possibilité d’explorer ces collections d’images, soit dans le but d’en extraire de l’information et de la connaissance, soit de permettre une certaine sérendipité dans l’exploration. Ainsi, cette problématique est abordée du point de vue de l’analyse et l’exploration interactive des données. Nous tirons profit du paradigme de navigation par similarité et visons à respecter simultanément les trois contraintes suivantes : (i) traiter de grandes collections d’images, (ii) traiter des collections dont le nombre d’images ne cesse de croître au cours du temps et (iii) donner des moyens d’explorer interactivement des collections d’images. Pour ce faire, nous proposons d’effectuer une étude conjointe de l’indexation et de la visualisation de grandes collections d’images qui s’agrandissent au cours du tempsThe research work that is presented and discussed in this thesis focuses on large and evergrowing image collections. More specifically, we aim at providing one the possibility to explore such image collections, either to extract some kind of information and knowledge, or to wander in the collections. This thesis addresses this issue from the perspective of Interactive Data Exploration and Analytics. We take advantage of the similarity-based image collection browsing paradigm and aim at meeting simultaneously the three following constraints: (i) handling large image collections, up to millions of images, (ii) handling dynamic image collections, to deal with ever-growing image collections, and (iii) providing interactive means to explore image collections. To do so, we jointly study the indexing and the interactive visualisation of large and ever-growing image collections
5
Goëau, Hervé. "Structuration de collections d'images par apprentissage actif crédibiliste." Phd thesis, Université Joseph Fourier (Grenoble), 2009. http://tel.archives-ouvertes.fr/tel-00410380.
Full textAbstract:
L'indexation des images est une étape indispensable pour valoriser un fond d'archive professionnel ou des collections d'images personnelles. Le "documentaliste" se doit de décrire précisément chaque document collecté dans la perspective de le retrouver. La difficulté est alors d'interpréter les contenus visuels et de les associer entre eux afin de couvrir différentes catégories qui peuvent être souvent très subjectives. Dans ce travail, nous nous inspirons du principe de l'apprentissage actif pour aider un utilisateur dans cette tâche de structuration de collections d'images. A partir de l'analyse des contenus visuels des images, différentes stratégies de sélection active sont développées afin d'aider un utilisateur à identifier et cerner des catégories pertinentes selon son point de vue. Nous proposons d'exprimer ce problème de classification d'images avec apprentissage actif dans le cadre du Modèle des Croyances Transférables (MCT). Ce formalisme facilite la combinaison, la révision et la représentation des connaissances que l'on peut extraire des images et des classes existantes à un moment donné. La méthode proposée dans ce cadre permet ainsi une représentation détaillée de la connaissance, notamment en représentant explicitement les cas d'appartenances à aucune ou à de multiples catégories, tout en quantifiant l'incertitude (liée entre autre au fossé sémantique) et le conflit entrainé par l'analyse des images selon différentes modalités (couleurs, orientations). Une interface homme-machine a été développée afin de valider notre approche sur des jeux de tests de référence, des collections d'images personnelles et des photographies professionnelles issues de l'Institut National de l'Audiovisuel. Une évaluation a été conduite auprès d'utilisateurs professionnels et a montré des résultats très positifs en termes d'utilité, d'utilisabilité et de satisfaction.
6
Kuzovkin, Dmitry. "Assessment of photos in albums based on aesthetics and context." Thesis, Rennes 1, 2019. http://www.theses.fr/2019REN1S032/document.
Full textAbstract:
Le processus de sélection de photos dans des albums peut être considérablement amélioré à l’aide d’un critère d’évaluation automatique des qualités d’une photo. Cependant, les méthodes existantes abordent ce problème de manière indépendante, c’est à dire en évaluant chaque image séparément des autres images d'un album. Dans cette thèse, nous explorons la modélisation du contexte d’une photo via une approche de clustering de collections de photos et la possibilité d'appliquer l’information de contexte à l'évaluation d’une photo. Nous avons effectué des études subjectives permettant d’étudier la manière dont les utilisateurs regroupent et sélectionnent des photos dans un album. Ces études ont permis une estimation du niveau de l’accord entre les différents utilisateurs. Nous avons aussi étudié la manière dont le contexte influence leurs décisions. Après avoir étudié la nature des décisions des utilisateurs, nous proposons une approche informatique pour modéliser leur comportement. Tout d'abord, nous introduisons une méthode de clustering hiérarchique, qui permet de regrouper des photos similaires selon une structure de similarité à plusieurs niveaux, basée sur des descripteurs visuels. Ensuite, les informations de contexte de la photo sont utilisées pour adapter le score de la photo pré-calculé indépendamment, en utilisant les données basées sur des statistiques et une approche d'apprentissage automatique. De plus, comme la majorité des méthodes récentes d'évaluation de la photo sont basées sur des réseaux de neurones convolutionnels, nous avons exploré et visualisé les caractéristiques esthétiques apprises par ces méthodesAn automatic photo assessment can significantly aid the process of photo selection within photo collections. However, existing computational methods approach this problem in an independent manner, by evaluating each image apart from other images in a photo album. In this thesis, we explore the modeling of photo context via a clustering approach for photo collections and the possibility of applying such context information in photo assessment. To better understand user actions within photo albums, we conduct experimental user studies, where we study how users cluster and select photos in photo collections. We estimate the level of agreement between users and investigate how the context, defined by similar photos in corresponding clusters, influences their decisions. After studying the nature of user decisions, we propose a computational approach to model user behavior. First, we introduce a hierarchical clustering method, which allows to group similar photos according to a multi-level similarity structure, based on visual descriptors. Then, the photo context information is extracted from the obtained cluster data and used to adapt a pre-computed independent photo score, using the statistics-based data and a machine learning approach. In addition, as the majority of recent methods for photo assessment are based on convolutional neural networks, we explore and visualize the aesthetic characteristics learned by such methods
7
Pommaret, Sabine. "Traitement documentaire et valorisation des fonds iconographiques anciens dans les bibliothèques l'exemple de la collection d'estampes de la B.M. de Bourges /." [S.l.] : [s.n.], 2002. http://www.enssib.fr/bibliotheque/documents/dcb/pommaret.pdf.
Full text
8
Assali, Camille. "Contribution des radars embarqués à l'étude des stratégies collectives de recherche alimentaire chez les oiseaux marins." Thesis, Montpellier, 2017. http://www.theses.fr/2017MONTT075/document.
Full textAbstract:
Dans l’océan, les bancs de proies représentent une source d’alimentation ponctuelle. Pour pallier à cela, les oiseaux marins profitent de l’information sociale provenant de conspécifiques, hétérospecifiques, ou bateaux de pêche. Dans cette thèse, nous cherchons à évaluer l’influence de différentes sources d’information sur les stratégies de recherche alimentaire des oiseaux marins en milieu pélagique tropical.Les oiseaux détectent des prédateurs ou des bateaux à des distances dépassant dix kilomètres. Nous étudions donc leur distribution à sub-méso-échelle, ceci grâce à des images d’un radar à bord d’un thonier senneur.Les images radar offrent une visualisation, dans les 30 km autour du navire, de la distribution instantanée de la communauté d’oiseaux en vol et de leurs déplacements. Nous mettons au jour des motifs d’agrégation temporaires, d’une dizaine de kilomètres de diamètre, au sein de la distribution des oiseaux. Les distances entre groupes d’oiseaux sont compatibles avec l’échange d’information au sein de ces agrégations.Une étude plus fine révèle des vols coordonnés de groupes d’oiseaux distants de plusieurs centaines de mètres («râteaux»), suggérant un haut degré de coopération lors de la recherche de proies. Nous questionnons ensuite le degré de perturbation du senneur dans la recherche alimentaire des oiseaux. Les résultats indiquent que les oiseaux marins discriminent les différentes activités du navire.Ce travail constitue, à notre connaissance, la première utilisation des radars embarqués pour l’étude de l’écologie des oiseaux en haute mer, et ouvre nombre de perspectives pour comprendre la dynamique des interactions entre prédateurs marins supérieursIn the ocean, prey is patchily distributed. To overcome this challenge, pelagic seabirds benefit from social information from conspecifics, heterospecifics, or fishing boats.As part of this dissertation, we aim at evaluating the influence of different information sources in seabird foraging strategies in the tropical pelagic environment.Seabirds can detect visible predators or boats at distances of over ten kilometres. We thus study the distribution of seabirds at sub-meso-scale, analysing images recorded from a radar on board a tuna purse-seiner. Radar images provide a visualisation of the instantaneous distribution of the in-flight seabird community as well as seabird movements within thirty kilometres of the seiner. We detect over-aggregatedand temporary patterns, spanning about ten kilometers, within flying seabirds’ distribution. Distancesbetween seabird groups are compatible with information exchanges within these aggregations. A finer scale study reveals coordinated flights of seabird groups distant of hundreds of meters from each others (« rakes »), and suggesting a high level of coordination during foraging. We then investigate the potential disturbance induced by the seiner in the seabirds’ foraging network.First results indicate that seabirds can discriminate the different seiner’s activities.To our knowledge, this work is the first contribution of on board radars use for the study of seabird ecology in the high seas, and opens interesting perspectives, such as the understanding of interactions’ dynamics within the marine top-predators guild
9
Mamdy, Bastien. "Nouvelle architecture de pixel CMOS éclairé par la face arrière, intégrant une photodiode à collection de trous et une chaine de lecture PMOS pour capteurs d’image en environnement ionisant." Thesis, Lyon, 2016. http://www.theses.fr/2016LYSE1197/document.
Full textAbstract:
Grâce à l'explosion du marché grand public des smartphones et tablettes, les capteurs d'image CMOS ont bénéficiés de développements technologiques majeurs leur permettant de rivaliser voir même de devancer les performances des capteurs CCD. En parallèle, dans les domaines de l'aérospatial ou de l'imagerie médicale, des capteurs CMOS ont également été développés pour des applications à fortes valeurs ajoutées avec des technologies reconnues pour leur robustesse en environnement ionisant. Le travail de cette thèse a pour but de réunir dans une même architecture de pixel les dernières avancées technologiques développées pour les capteurs grands publics avec une solution novatrice de durcissement aux rayonnements ionisants récemment développée chez STMicroelectronics. Pour la première fois, cette nouvelle architecture de pixel de 1,4µm de côté et éclairée par la face arrière intègre une photodiode pincée verticale à collection de trous, une chaine de lecture composée de transistors PMOS et des tranchées d'isolation profondes à passivation passive ou active. Ce type de pixel a été conçu à l'aide de simulations TCAD en trois dimensions qui ont permis d'optimiser l'intégration de procédés pour sa fabrication. Il a été caractérisé et comparé à un pixel équivalent de type N avant et après irradiation par rayonnement gamma. Le pixel développé au cours de cette thèse présente intrinsèquement un plus faible courant d'obscurité que son homologue de type N et une meilleure résistance aux radiations. La passivation active des tranchées d'isolation profondes permet d'atténuer fortement l'impact des dégradations habituellement observées au niveau des interfaces Si/SiO2 et s'avère donc prometteuse en environnement ionisant. Des mécanismes intrinsèquement différents de formation de pixels blancs sous irradiation ont été mis en évidence pour les pixels de type P et de type N. Enfin, les technologies de l'éclairement par la face arrière et de la photodiode verticale contribuent chacune à la bonne efficacité quantique du pixel ainsi qu'à sa capacité de stockage importanteThanks to the growing smartphones and tablets consumer markets, CMOS image sensors have benefited from major technology developments and are able to rival with and even outperform CCD sensors. In parallel, for spatial and medical imaging applications, CMOS sensors have been developed using technologies recognized for their robustness in harsh ionizing environment. This Ph.D. thesis work aims at combining in one single pixel architecture the latest technology developments driven by consumer applications with a novel solution for radiation hardening recently developed at STMicroelectronics. For the first time, this innovative back-side illuminated pixel architecture integrates within a 1.4µm pitch a vertical pinned photodiode based on hole-collection, a PMOS readout chain and deep trench isolation with either passive or active interface passivation. This pixel has been developed using 3D-TCAD simulations allowing fast and efficient optimization of its fabrication process. Through a series of electro-optical characterizations, we have compared its performances to its N-type equivalent before and after irradiation with gamma rays. The pixel developed during this thesis exhibits intrinsically lower level of dark current than its N-type counterpart and improved radiation hardness. Active passivation of deep trench isolation greatly decreases the impact of degradations usually observed at Si/SiO2 interfaces and therefore shows very promising results in ionizing environment. Evidence of intrinsically different mechanisms of white pixel formation under irradiation for N-type and P-type pixels have been presented. Finally, back-side illumination technology and the vertical photodiode both contribute to the pixel’s high full well capacity and good quantum efficiency
10
Muhesen, Nibal. "Le roi et son image en Syrie au bronze moyen : étude iconographique d’après la glyptique et d’autres documents figurés et écrits." Thesis, Lyon 2, 2009. http://www.theses.fr/2009LYO20081.
Full textAbstract:
Cette thèse a pour objectif d’étudier la « figure du roi » au travers de documents iconographiques du Bronze Moyen provenant de Syrie et plus particulièrement de la zone du Moyen-Euphrate entre 2000 et 1600 avant J.-C. Notre approche méthodologique qui porte prioritairement sur la partie sigillaire a consisté à établir un corpus des plus exhaustifs possibles des sceaux publiés et inédits. Après l’établissement de celui-ci, nous opérons des comparaisons pour dégager les caractéristiques de la représentation royale. Dans un premier temps, le cadre spatio-temporel retenu pour cette étude est défini. Par la suite, nous effectuons une mise au point sur l’histoire de la question de la représentation royale dans la glyptique syrienne du Bronze Moyen. Le développement qui suit constitue la cible de cette thèse. Les objets qui servent de base à cette étude viennent de vingt cinq sites archéologiques différents. Les sites de Moyen-Euphrate syrien, divisés en deux ensembles : partie nord et partie sud couvrant la zone-clefs de cette thèse, ont été soigneusement étudiés. En suite et afin de mieux définir la « figure du roi » dans l’iconographie, des moyens d’identification ont été décrits. La suite comporte une analyse de toutes les représentations de la figure royale, que nous tentons de définir par type. Le paragraphe présentant chaque modèle est suivi d’un tableau montrant l’aire de diffusion au sein de l’aire géographique concernée. Suit un inventaire des multiples aspects de cette iconographie royale, au sein duquel on distingue des : 1. Modèles dominants: le roi à la masse d’arme, le roi vainqueur, le roi-orant et le roi de type « syrien » que nous tentons de définir.2. Modèles dérivés: le roi-porteur d’offrande, représentation royale avec une divinité féminine, le roi-pharaon de type «égyptien », les cas de la duplication de la figure royale.Par ailleurs, une étude des « personnages incertaines » que nous expliquons est également menée. La présence de multiples divinités aux côtés des rois nous a conduits à en effectuer l’inventaire et à en préciser dans la mesure du possible l’iconographie, le cas échéant à préciser la nature des cultes qui leur étaient rendus. Cependant, des questions importantes, comme la compréhension de certaines réalités telles que la question complexe de la« divinisation ou non du personnage royal », ou les « Dieux politiques » ont été posées. De plus, des problèmes tels que le rite de « kispûm » ou la question de « Dieu de roi » ont été abordés. Parmi nos conclusions les plus importants on souligne : l’aspect régional de l’image du roi en Syrie, le rapport particulier entre l’archéologie et la glyptique ainsi que le fond sacré de l’idéologie royale de l’époque amorrite. Au niveau de l’organisation de cette thèse, notre premier volume est accompagné d’un second volume représentant le catalogne des matériels étudiés (env. quatre cent objets). L’ensemble est complété par deux index et de références bibliographiquesThis doctorate (Ph.D.) research studies the representation of Syrian kingship during the Amorite period (ca. 2000-1600 B.C), essentially through glyptic evidence, supplemented by sculpture, wall paintings, and written sources from the same period.The methodology is anchored in defining a precise iconographic corpus. This step allows revising past conclusions and establishing new identifications for the king’s role in artistic as well as written expressions. A major accomplishment is the identification of objects that derive from clear, stratified archaeological and cultural contexts.After defining the spatial and chronological frame, this study offers a brief review of the twenty-five sites from which the material is assembled. They are located in the Middle-Euphrates valley and divide between those in the northern and southern segments. Characteristics for a “royal figure” are identified and then defended. Iconography permits to distinguish diverse models of the “royal for each of the Syrian regions.The models divide into:1. Main models: the warrior-king, the king-priest, the king of “Syrian” type2. Secondary models: royal officials or the “duplication” of the royal figureIn addition, “miscellaneous figures” are also classified.On the epigraphic level, in this study there is liberal use of information from the archive of Mari as well as of Terqa, discriminating between materials derived from epistolary, religious, political, and administrative documents, as the ruler acts as a priest, dispenser of justice, warrior, or family man. A special chapter is devoted the interrelationship among kings, personal, and state gods. There is also consideration of funerary rituals (kispum) as well as the issue of the deified king.The study takes into consideration the following issues: the royal image of Syrian kings as shown in regional perspective, the connection between glyptic arts and their archeology, and the religious basis of royal ideology during the Amorite period.The dissertation includes a second part in which is catalogued over four hundred iconographic objects or images. Bibliographic references and indexes complete the study
Books on the topic "Document image collections"
1
Council on Library and Information Resources. Commission on Preservation and Access. and Council on Library and Information Resources. Digital Libraries., eds. Digitizing historical pictorial collections for the Internet. Washington, D.C: Council on Library and Information Resources, 1998.
Find full text
2
Council on Library and Information Resources. and European Commission on Preservation and Access., eds. Digitizing historical pictorial collections for the Internet. Amsterdam: European Commission on Preservation and Access, 1998.
Find full text
3
Dibazar, Pedram, and Judith Naeff, eds. Visualizing the Street. NL Amsterdam: Amsterdam University Press, 2018. http://dx.doi.org/10.5117/9789462984356.
Full textAbstract:
From user-generated images of streets to professional architectural renderings, and from digital maps and drone footages to representations of invisible digital ecologies, this collection of essays analyses the emergent practices of visualizing the street. Today, advancements in digital technologies of the image have given rise to the production and dissemination of imagery of streets and urban realities in multiple forms. The ubiquitous presence of digital visualizations has in turn created new forms of urban practice and modes of spatial encounter. Everyone who carries a smartphone not only plays an increasingly significant role in the production, editing and circulation of images of the street, but also relies on those images to experience urban worlds and to navigate in them. Such entangled forms of image-making and image-sharing have constructed new imaginaries of the street and have had a significant impact on the ways in which contemporary and future streets are understood, imagined, documented, navigated, mediated and visualized. Visualizing the Street investigates the social and cultural significance of these new developments at the intersection of visual culture and urban space. The interdisciplinary essays provide new concepts, theories and research methods that combine close analyses of street images and imaginaries with the study of the practices of their production and circulation. The book covers a wide range of visible and invisible geographies — From Hong Kong’s streets to Rio’s favelas, from Sydney’s suburbs to London’s street markets, and from Damascus’ war-torn streets to Istanbul’s sidewalks — and engages with multiple ways in which visualizations of the street function to document street protests and urban change, to build imaginaries of urban communities and alternate worlds, and to help navigate streetscapes.
4
Paris (France). Mairie annexe du IVe Arrondissement, ed. Fières archives: Documents et images autobiographiques d'homosexuels "fin de siècle". Neuilly: Atlande, 2017.
Find full text
5
Yves, Desrichard, ed. Cinéma en bibliothèque. Paris: Electre/Cercle de la librairie, 2004.
Find full text
6
Yves, Alix, Vernet Marc, and Desrichard Yves, eds. Cinéma en bibliothèque. Paris: Cercle de la librairie, 2004.
Find full text
7
Grandin, Karl, Nils Olander, Piero Mazzinghi, and Giuseppe Pelosi, eds. A Wireless World. One Hundred Years since the Nobel Prize to Guglielmo Marconi. Florence: Firenze University Press, 2012. http://dx.doi.org/10.36253/978-91-7190-179-8.
Full textAbstract:
The volume is dedicated to the one hundred years since Guglielmo Marconi was awarded the Nobel Prize (1909). The choice of honoring Marconi in this centennial occasion stems from the huge impact that wireless communications had on society. The book is divided into four parts covering the life of Marconi and his environment up to the Nobel Prize: "Part I – Documents," comprehends four contributions tightly linked to the Nobel Prize awarding to Marconi in 1909. "Part II - Marconi road to the Nobel Prize," proposes some deepening on the work of Marconi before his Nobel Prize, relevant to his scientific education and to particular and not well known events in the years of his first experiments. "Part III - Marconi's contemporary and later related scientists," presents Ferdinand Braun, who shared the Nobel Prize with Marconi, as well as other scientists related to wireless communications. "Part IV - Devices and collections in Sweden and Italy," shows a selection of the cultural heritage, Italian and Swedish, about the history of telecommunications engineering. The book presents several images and illustrations, some of which published here for the first time.
8
Geneviève, Contamine, Labie-Leurquin A. -F, Peyrafort-Huin M, Institut de recherche et d'histoire des textes (France), and Centre national de la recherche scientifique (France), eds. Recherche et histoire des textes: Filmothèques, photothèques et techniques nouvelles : colloque international organisé à l'occasion du cinquantenaire de l'Institut de recherche et d'histoire des textes, Paris-Orléans, 23-25 novembre 1987 : images des textes, les techniques de reproduction des documents médiévaux au service de la Recherche. Paris: Léopard d'or, 1992.
Find full text
9
Digital imaging: A practical handbook. London: Facet Pub., 2002.
Find full text
10
Digital imaging: A practical handbook. New York: Neal-Schuman Publishers in association with Library Association Pub., 2001.
Find full textBook chapters on the topic "Document image collections"
1
Balasubramanian, A., Million Meshesha, and C. V. Jawahar. "Retrieval from Document Image Collections." In Document Analysis Systems VII, 1–12. Berlin, Heidelberg: Springer Berlin Heidelberg, 2006. http://dx.doi.org/10.1007/11669487_1.
Full text
2
Wilkinson, Tomas, and Anders Brun. "Visualizing Document Image Collections Using Image-Based Word Clouds." In Advances in Visual Computing, 297–306. Cham: Springer International Publishing, 2015. http://dx.doi.org/10.1007/978-3-319-27857-5_27.
Full text
3
Molina, Adrià, Lluis Gomez, Oriol Ramos Terrades, and Josep Lladós. "A Generic Image Retrieval Method for Date Estimation of Historical Document Collections." In Document Analysis Systems, 583–97. Cham: Springer International Publishing, 2022. http://dx.doi.org/10.1007/978-3-031-06555-2_39.
Full text
4
Huber-Mörk, Reinhold, and Alexander Schindler. "Quality Assurance for Document Image Collections in Digital Preservation." In Advanced Concepts for Intelligent Vision Systems, 108–19. Berlin, Heidelberg: Springer Berlin Heidelberg, 2012. http://dx.doi.org/10.1007/978-3-642-33140-4_10.
Full text
5
Graf, Roman, Reinhold Huber-Mörk, Alexander Schindler, and Sven Schlarb. "An Expert System for Quality Assurance of Document Image Collections." In Progress in Cultural Heritage Preservation, 251–60. Berlin, Heidelberg: Springer Berlin Heidelberg, 2012. http://dx.doi.org/10.1007/978-3-642-34234-9_25.
Full text
6
Huber-Mörk, Reinhold, and Alexander Schindler. "An Image Based Approach for Content Analysis in Document Collections." In Advances in Visual Computing, 278–87. Berlin, Heidelberg: Springer Berlin Heidelberg, 2013. http://dx.doi.org/10.1007/978-3-642-41939-3_27.
Full text
7
Ngo, Vuong M., Gary Munnelly, Fabrizio Orlandi, Peter Crooks, Declan O’Sullivan, and Owen Conlan. "A Semantic Search Engine for Historical Handwritten Document Images." In Linking Theory and Practice of Digital Libraries, 60–65. Cham: Springer International Publishing, 2021. http://dx.doi.org/10.1007/978-3-030-86324-1_7.
Full textAbstract:
AbstractA very large number of historical manuscript collections are available in image formats and require extensive manual processing in order to search through them. So, we propose and build a search engine for automatically storing, indexing and efficiently searching the manuscript images. Firstly, a handwritten text recognition technique is used to convert the images into textual representations. In the next steps, we apply the named entity recognition and historical knowledge graph to build a semantic search model, which can understand the user’s intent in the query and the contextual meaning of concepts in documents, to return correctly the transcriptions and their corresponding images for users.
8
Gil-García, Reynaldo, and Aurora Pons-Porrata. "A Speed-Up Hierarchical Compact Clustering Algorithm for Dynamic Document Collections." In Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications, 379–86. Berlin, Heidelberg: Springer Berlin Heidelberg, 2009. http://dx.doi.org/10.1007/978-3-642-10268-4_45.
Full text
9
Pramod Sankar, K., and C. V. Jawahar. "Enabling Search over Large Collections of Telugu Document Images – An Automatic Annotation Based Approach." In Computer Vision, Graphics and Image Processing, 837–48. Berlin, Heidelberg: Springer Berlin Heidelberg, 2006. http://dx.doi.org/10.1007/11949619_75.
Full text
10
Gey, Fredric C. "Searching a Russian Document Collection Using English, Chinese and Japanese Queries." In Multilingual Information Access for Text, Speech and Images, 200–206. Berlin, Heidelberg: Springer Berlin Heidelberg, 2005. http://dx.doi.org/10.1007/11519645_21.
Full textConference papers on the topic "Document image collections"
1
Agam, G., S. Argamon, O. Frieder, D. Grossman, and D. Lewis. "Content-based document image retrieval in complex document collections." In Electronic Imaging 2007, edited by Xiaofan Lin and Berrin A. Yanikoglu. SPIE, 2007. http://dx.doi.org/10.1117/12.703163.
Full text
2
K., Pramod Sankar. "Reverse annotation based retrieval from large document image collections." In Proceeding of the 33rd international ACM SIGIR conference. New York, New York, USA: ACM Press, 2010. http://dx.doi.org/10.1145/1835449.1835694.
Full text
3
Graf, Roman, Reinhold Huber-Mörk, Alexander Schindler, and Sven Schlarb. "Duplicate detection approaches for quality assurance of document image collections." In the Fifth International Conference. New York, New York, USA: ACM Press, 2013. http://dx.doi.org/10.1145/2536146.2536157.
Full text
4
Huber-Mork, Reinhold, and Alexander Schindler. "Automatic classification of defect page content in scanned document collections." In 2013 8th International Symposium on Image and Signal Processing and Analysis (ISPA). IEEE, 2013. http://dx.doi.org/10.1109/ispa.2013.6703735.
Full text
5
Saund, Eric. "A Graph Lattice Approach to Maintaining Dense Collections of Subgraphs as Image Features." In 2011 International Conference on Document Analysis and Recognition (ICDAR). IEEE, 2011. http://dx.doi.org/10.1109/icdar.2011.216.
Full text
6
Gershbock, Richard. "Image acquisition: quality control for document image scanners." In Critical Review Collection. SPIE, 1991. http://dx.doi.org/10.1117/12.48889.
Full text
7
Arijs, Hilke. "I value, you value, we value… but what’s the value?" In SOIMA 2015: Unlocking Sound and Image Heritage. International Centre for the Study of the Preservation and Restoration of Cultural Property, 2017. http://dx.doi.org/10.18146/soima2015.2.09.
Full textAbstract:
Today‚ audiovisual collections account for a large portion of the world’s memory. They are part of museums, serve as research documents for various types of scientific institution, register history and provide us with a tangible witness of our most precious memories. Even though sound and image collections are generally accepted as being part of our cultural heritage, determining how to open such collections to a large audience is far from simple. Although value and signi cance assessments are increasingly used as collection management tools, they are labour intensive and organizationally demanding activities for collection managers and institutions. Nevertheless such assessments are vital to ensure proper collection management today and in the future. Likewise they provide us with an excellent tool in communicating about audiovisual collections, prioritizing in case of digitization and rendering their management comprehensible. This paper outlines a three-step methodology designed to facilitate assessing value in audiovisual collections.
8
Ferranti, Tomás, Asla Medeiros e Sá, and Paulo Cezar Pinto Carvalho. "Single Image 3D Building Reconstruction Using Rectangles Parallel to an Axis." In Workshop de Visão Computacional. Sociedade Brasileira de Computação - SBC, 2021. http://dx.doi.org/10.5753/wvc.2021.18906.
Full textAbstract:
Historic photographic collections are valuable documents of urban evolution through time. Many historic buildings documented in such collections may have been demolished or changed over time. Digital modeling such buildings may be challenging due to the reduced amount of information available that may be limited to a few images and/or schematic drawings. This paper presents a method to create a 3D set of rectangles that approximates elements of a scene (such as walls, floors, and roofs) from a single image. Using a pinhole camera model, the extraction of geometry and texture of planes parallel to an axis can be obtained after a camera calibration step that recovers intrinsic parameters of the model. Results show that a good visualization of the scene can be created, using the proposed technique, from a single image.
9
Josi, Frieda, Christian Wartena, and Ulrich Heid. "Preparing Legal Documents for NLP Analysis: Improving the Classification of Text Elements by Using Page Features." In 8th International Conference on Natural Language Processing (NATP 2022). Academy and Industry Research Collaboration Center (AIRCC), 2022. http://dx.doi.org/10.5121/csit.2022.120102.
Full textAbstract:
Legal documents often have a complex layout with many different headings, headers and footers, side notes, etc. For the further processing, it is important to extract these individual components correctly from a legally binding document, for example a signed PDF. A common approach to do so is to classify each (text) region of a page using its geometric and textual features. This approach works well, when the training and test data have a similar structure and when the documents of a collection to be analyzed have a rather uniform layout. We show that the use of global page properties can improve the accuracy of text element classification: we first classify each page into one of three layout types. After that, we can train a classifier for each of the three page types and thereby improve the accuracy on a manually annotated collection of 70 legal documents consisting of 20,938 text elements. When we split by page type, we achieve an improvement from 0.95 to 0.98 for single-column pages with left marginalia and from 0.95 to 0.96 for double-column pages. We developed our own feature-based method for page layout detection, which we benchmark against a standard implementation of a CNN image classifier.
10
Loconsole, Claudio, Marianna Giardina, and Enrica Salvatori. "ArchiVico Digitale: a comprehensive and synergistic approach for the preservation and dissemination of local memory to strengthen identity." In 14th International Conference on Applied Human Factors and Ergonomics (AHFE 2023). AHFE International, 2023. http://dx.doi.org/10.54941/ahfe1003699.
Full textAbstract:
The main objectives of the "ArchiVico Digitale" project are the digitization, cataloging and web publication on an Omeka-based platform of the documentary material preserved in the Historical Archive of Vicopisano (HAV) to facilitate the access to several documents and the exploration of thematic discovery paths linked to local historical memory.The result of the publication of this material on the web is a digital archive collecting and enhancing archival documents to allow scholars and the general public to carry out research. Since the HAV keeps a large number of documents gathered in files, a preliminary selection of two types of documents/files was necessary: those in a poor state of conservation and those of extreme interest which bear witness to relations with the territory and historical dynamics. The proposed approach, implemented in synergy between different public and private subjects, provides the restoration of documents in a poor state of conservation, the digitization and archival description of each selected document, the web publication in a digital archive and the dissemination of the contents of the documents relating to local historical dynamics to students of schools of all levels in educational courses aimed at preserving the collective historical memory. The project, conducted in a three-year period, resulted in 12 thematic paths for a total of 194 documents (765 image files), a total of 6 restored archives (5,130 image files) and a dissemination activity of the thematic itineraries involving a total of over 160 students and over 15 teachers.
Reports on the topic "Document image collections"
1
Sharpe, D. R., G. Leduc, C. S. Smart, and J. Shaw. Georgian Bay bedrock erosion: evidence for regional floods, Ontario. Natural Resources Canada/CMSS/Information Management, 2023. http://dx.doi.org/10.4095/331409.
Full textAbstract:
We provide an updated presentation of the spectacular erosion forms at French River Ontario (Kor et al. 1991) based on new methods of data collection and wider observations. This work includes ~ 10 more detailed study sites, documentation of the range of forms over a larger area, the use of extensive drone image capture and ground surveys, as well as a detailed inventory of forms. Key sites are illustrated using video images. The update extends the conclusions of the Kor paper regarding the significance and scale of subglacial meltwater erosion with some novel findings. We document the importance of plucking (including hydraulic plucking) and, the control of structure on s-forms, which were not highlighted in the Kor study. Apparent cavitation erosion forms are prominent across the study area and provide support for inferred high-velocity meltwater flow. A growing interpretative framework includes discussion of evidence to test a theorized hydraulic sequence of sheet-channel-distributed flow, followed by re-grounding of glacial ice as meltwater flow waned. This hydraulic sequence may also be complementary to observations in thick sediment terrain down flow.
2
Khan, Mahreen. The Environmental Impacts of War and Conflict. Institute of Development Studies, March 2022. http://dx.doi.org/10.19088/k4d.2022.060.
Full textAbstract:
In modern warfare, the first widely acknowledged scientific study and documented case of environmental damage during conflict was the (direct and deliberate) use of Agent Orange and other toxic chemicals by US forces, from 1961-1971, during the Vietnam War in a policy known as herbicide. The Vietnam War has been relatively well documented for the sheer horror and magnitude of the devastation to natural habitats and because it was the first war where television and global media brought vivid images and accounts into people’s homes, making the war a matter of political and public conscience This helped stir academic and scientific interest and facilitated evidence collection and documentation of environmental damages. This helpdesk report is a rapid literature review on the main environmental impacts of war and conflict, drawing primarily on academic, and peer reviewed literature and only some policy and practitioner sources, as per the request. Where current situations are discussed, such as the ongoing Ukraine war, a few blogs are referred to. Within the literature focused on the environmental impacts of conflict, common case studies include: the North Atlantic Treaty Organisation (NATO) bombing of Kosovo (1999), and the conflict in the Donbas region of Ukraine (2014). Interestingly there is comparatively less literature on the conflicts in Afghanistan (2001-2021), the Iraq-Iran War (1980-1988), the Gulf Wars (1991 and 2003), the Yemeni civil war (2014 – present) and the ongoing war in Syria (since 2011) despite their relatively greater severity, intensity and duration.
3
L51815 The Development of a TOFD Image Reference Collection. Chantilly, Virginia: Pipeline Research Council International, Inc. (PRCI), June 1997. http://dx.doi.org/10.55274/r0010365.
Full textAbstract:
The Time Of Flight Diffraction (TOFD) Technique is rapidly gaining importance as a reliable NDT technique for weld inspection, capable of both detection and sizing of defects. The acquisition of TOFD inspection data is fast and straightforward; the crucial step in inspection reliability is therefore its interpretation. A reliable interpretation of TOFD images requires considerable training and skill, and in that respect bears resemblance to the interpretation of radiographic images. Therefore a need was recognized to develop a TOFD Image Reference Collection, by analogy with the existing and widely known IIW Collection of Reference Radiographs of Welds in Steel, to assist TOFD operators in analyzing images. The objective to arrive at a reference collection of TOFD Images. The TOFD image collection is a stand-alone document. Revision 0 contains, apart from typical inspection results for most defect types, an extensive introduction describing purpose, scope and instructions for use.