The Experts below are selected from a list of 3528 Experts worldwide ranked by ideXlab platform
Faisal Shafait - One of the best experts on this subject based on the ideXlab platform.
-
Logical Layout analysis using deep learning
Digital Image Computing: Techniques and Applications, 2019Co-Authors: Annus Zulfiqar, Adnan Ulhasan, Faisal ShafaitAbstract:Logical Layout analysis plays an important part in document understanding. It can become a challenging task due to varying formats and Layouts. Researchers have proposed different ways to solve this problem, mostly using visual information in some way and a complex pipeline. In this paper, we present a simple technique for labelling the Logical structures in document images. We use visual and textual features from the document images to label zones. We utilize Recurrent Neural Networks, specifically 2 layers of LSTM, which input the text from the zone that we want to classify as sequences of words and the normalized position of each word with respect to the page width and height. Comparisons are made by comparing the image under test with the known Layouts and labels are assigned to zones accordingly. The labels are abstract, title, author names, and affiliation; however, the text also contains very important information for the task at hand. The presented approach achieved an overall accuracy of 96.21% on publicly available MARG dataset.
-
analysis of the Logical Layout of documents
Handbook of Document Image Processing and Recognition, 2014Co-Authors: Andreas Dengel, Faisal ShafaitAbstract:Automatic document understanding is one of the most important tasks when dealing with printed documents since all post-ordered systems require the captured but process-relevant data. Analysis of the Logical Layout of documents not only enables an automatic conversion into a semantically marked-up electronic representation but also reveals options for developing higher-level functionality like advanced search (e.g., limiting search to titles only), automatic routing of business letters, automatic processing of invoices, and developing link structures to facilitate navigation through books. Over the last three decades, a number of techniques have been proposed to address the challenges arising in Logical Layout analysis of documents originating from many different domains. This chapter provides a comprehensive review of the state of the art in the field of automated document understanding, highlights key methods developed for different target applications, and provides practical recommendations for designing a document understanding system for the problem at hand.
Bandik Matej - One of the best experts on this subject based on the ideXlab platform.
-
Portal Game for Microsoft HoloLens
Vysoké učení technické v Brně. Fakulta informačních technologií, 2019Co-Authors: Bandik MatejAbstract:Cieľom práce bolo vytvoriť adaptáciu počítačovej hry Portal pre zariadenie Microsoft HoloLens. Požadovaná aplikácia by mala demonštrovať koncept hry v reálnom prostredí. Ďalším dôležitým požiadavkom bolo užívateľa úplne oprostiť od použitia počítačového príslušenstva a presunúť rozhranie celej aplikácie do reálneho priestoru. Výsledkom je natívna aplikácia pre Universal Windows Platform, ktorá prevádza herné mechaniky a modely hry Portal z počítačového 2D prostredia do reálneho 3D priestoru. V jej hlavnej časti je užívateľ zasadený do role riešiteľa logických hádaniek, v ktorých využíva gestá na manipuláciu s hologramami či aktiváciu rôznych mechanik. Druhá časť užívateľovi sprístupňuje možnosť pretvárať reálne prostredie vkladaním virtuálnych objektov. Ich logickým usporiadaním môže vytvárať rôzne riešiteľné hádanky priamo v priestore, v ktorom sa nachádza. Vytvorená aplikácia efektívne využíva rozšírenú realitu a možnosti zariadenia Microsoft HoloLens na prezentáciu základného konceptu hry Portal.Goal of this work is to create an adaptation of computer game Portal for device Microsoft HoloLens. Required application should be able to demonstrate concept of the game in real environment. Next important requirement was to move interface of whole application to real space. The result is native application for Universal Windows Platform, which converts game mechanics and models of game Portal from computer 2D space to real 3D space. In the main part, user is set to the role of an player of Logical puzzles, in which he is using gestures for manipulating with holograms or activation of several mechanics. Second part opens possibility to recreate real space by inserting virtual objects. By their Logical Layout, user can create different solvable puzzles directly in space, in which he is located. Created application effectively uses augmented reality and possibilities of Microsoft HoloLens device for presentation of main concept of game Portal.
-
Portal Game for Microsoft HoloLens
Vysoké učení technické v Brně. Fakulta informačních technologií, 2019Co-Authors: Bandik MatejAbstract:Goal of this work is to create an adaptation of computer game Portal for device Microsoft HoloLens. Required application should be able to demonstrate concept of the game in real environment. Next important requirement was to move interface of whole application to real space. The result is native application for Universal Windows Platform, which converts game mechanics and models of game Portal from computer 2D space to real 3D space. In the main part, user is set to the role of an player of Logical puzzles, in which he is using gestures for manipulating with holograms or activation of several mechanics. Second part opens possibility to recreate real space by inserting virtual objects. By their Logical Layout, user can create different solvable puzzles directly in space, in which he is located. Created application effectively uses augmented reality and possibilities of Microsoft HoloLens device for presentation of main concept of game Portal
Atanassova Iana - One of the best experts on this subject based on the ideXlab platform.
-
Dataset for Logical-Layout analysis on French historical newspapers
HAL CCSD, 2021Co-Authors: Gutehrlé Nicolas, Atanassova IanaAbstract:This dataset is intended for training and testing Logical Layout Analysis and recognition system on French historical documents published between 1900 and 1950. The original data is part of the "Fond régional: Franche-Comté", which is curated by Gallica, the digital portal of the Bibliothèque Nationale de France (BnF). It is available on Zenodo at the following adress: https://zenodo.org/record/5752440#.YboX6lPjJhEThis dataset is intended for training and testing Logical Layout Analysis and recognition system on French historical documents published between 1900 and 1950. The original data is part of the "Fond régional: Franche-Comté", which is curated by Gallica, the digital portal of the Bibliothèque Nationale de France (BnF). It is available on Zenodo at the following adress: https://zenodo.org/record/5752440#.YboX6lPjJh
-
Logical Layout Analysis Applied to Historical Newspapers
HAL CCSD, 2021Co-Authors: Gutehrlé Nicolas, Atanassova IanaAbstract:In recent years, libraries and archives led important digitisation campaigns that opened the access to vast collections of historical documents. While such documents are often available as XML ALTO documents, they lack information about their Logical structure. In this paper, we address the problem of Logical Layout analysis applied to historical documents. We propose a method which is based on the study of a dataset in order to identify rules that assign Logical labels to both block and lines of text from XML ALTO documents. Our dataset contains newspapers in French, published in the first half of the 20th century. The evaluation shows that our methodology performs well for the identification of first lines of paragraphs and text lines, with F1 above 0.9. The identification of titles obtains an F1 of 0.64. This method can be applied to preprocess XML ALTO documents in preparation for downstream tasks, and also to annotate largescale datasets to train machine learning and deep learning algorithms
Annus Zulfiqar - One of the best experts on this subject based on the ideXlab platform.
-
Logical Layout analysis using deep learning
Digital Image Computing: Techniques and Applications, 2019Co-Authors: Annus Zulfiqar, Adnan Ulhasan, Faisal ShafaitAbstract:Logical Layout analysis plays an important part in document understanding. It can become a challenging task due to varying formats and Layouts. Researchers have proposed different ways to solve this problem, mostly using visual information in some way and a complex pipeline. In this paper, we present a simple technique for labelling the Logical structures in document images. We use visual and textual features from the document images to label zones. We utilize Recurrent Neural Networks, specifically 2 layers of LSTM, which input the text from the zone that we want to classify as sequences of words and the normalized position of each word with respect to the page width and height. Comparisons are made by comparing the image under test with the known Layouts and labels are assigned to zones accordingly. The labels are abstract, title, author names, and affiliation; however, the text also contains very important information for the task at hand. The presented approach achieved an overall accuracy of 96.21% on publicly available MARG dataset.
Gutehrlé Nicolas - One of the best experts on this subject based on the ideXlab platform.
-
Dataset for Logical-Layout analysis on French historical newspapers
HAL CCSD, 2021Co-Authors: Gutehrlé Nicolas, Atanassova IanaAbstract:This dataset is intended for training and testing Logical Layout Analysis and recognition system on French historical documents published between 1900 and 1950. The original data is part of the "Fond régional: Franche-Comté", which is curated by Gallica, the digital portal of the Bibliothèque Nationale de France (BnF). It is available on Zenodo at the following adress: https://zenodo.org/record/5752440#.YboX6lPjJhEThis dataset is intended for training and testing Logical Layout Analysis and recognition system on French historical documents published between 1900 and 1950. The original data is part of the "Fond régional: Franche-Comté", which is curated by Gallica, the digital portal of the Bibliothèque Nationale de France (BnF). It is available on Zenodo at the following adress: https://zenodo.org/record/5752440#.YboX6lPjJh
-
Logical Layout Analysis Applied to Historical Newspapers
HAL CCSD, 2021Co-Authors: Gutehrlé Nicolas, Atanassova IanaAbstract:In recent years, libraries and archives led important digitisation campaigns that opened the access to vast collections of historical documents. While such documents are often available as XML ALTO documents, they lack information about their Logical structure. In this paper, we address the problem of Logical Layout analysis applied to historical documents. We propose a method which is based on the study of a dataset in order to identify rules that assign Logical labels to both block and lines of text from XML ALTO documents. Our dataset contains newspapers in French, published in the first half of the 20th century. The evaluation shows that our methodology performs well for the identification of first lines of paragraphs and text lines, with F1 above 0.9. The identification of titles obtains an F1 of 0.64. This method can be applied to preprocess XML ALTO documents in preparation for downstream tasks, and also to annotate largescale datasets to train machine learning and deep learning algorithms
