Filters








55,419 Hits in 3.6 sec

Document inspection using text-line alignment

Joost van Beusekom, Faisal Shafait, Thomas M. Breuel
2010 Proceedings of the 8th IAPR International Workshop on Document Analysis Systems - DAS '10  
Therefore, so called second line inspection, using machines to testify a documents originality could be suitable.  ...  DECISION MAKING Using the alignment lines, the distances of the respective text-line points to the alignment lines can be computed.  ... 
doi:10.1145/1815330.1815364 dblp:conf/das/BeusekomSB10 fatcat:mhhwjwctj5a77kucxfl3lrzr44

Lessons Learned from Automatic Forgery Detection in over 100,000 Invoices [chapter]

Joost van Beusekom, Armin Stahl, Faisal Shafait
2015 Lecture Notes in Computer Science  
Besides several advantages of this automated processing, it complicates the first line inspection of incoming documents which are often of vital financial or legal relevance.  ...  We have developed a number of different techniques to allow automatic detection of forged or manipulated documents over the last years.  ...  The distances of the start and end point of the text-lines to the respective alignment lines are used as features to decide if the text-line has a suspicious distance to either of the alignment lines or  ... 
doi:10.1007/978-3-319-20125-2_12 fatcat:vcvh2wmgjjesjlork4nlgovsme

User-assisted alignment of Arabic historical manuscripts

Abedelkadir Asi, Irina Rabaev, Klara Kedem, Jihad El-Sana
2011 Proceedings of the 2011 Workshop on Historical Document Imaging and Processing - HIP '11  
The user selects the region to align in two manuscripts and the system return its alignment with visual clues that indicate the distance between the aligned components.  ...  We adopted the edit distance, which is computed using dynamic time warping (DTW) on the feature domain, to measure similarity between components.  ...  [2] segmented handwritten documents into text lines, generated different word segmentation for each line, and selected the best alignment between the word of the transcription and the result of a word  ... 
doi:10.1145/2037342.2037347 dblp:conf/icdar/AsiRKE11 fatcat:76qkfe3c7vezzolzrrh7ftugzq

Interactive Exploration and Flattening of Deformed Historical Documents

Kazim Pal, Melissa Terras, Tim Weyrich
2013 Computer graphics forum (Print)  
local region under inspection.  ...  Figure 1 : From left to right: A 3D reconstruction of a damaged parchment, a global flattening of the parchment, a locally-affine undistortion of a section of the text, and a local flattening of that same  ...  We use V to solve goal (3). We can rectify the text since V encodes the local orientation of the text at each point, and can navigate along lines of text by moving through the flow lines of V .  ... 
doi:10.1111/cgf.12052 fatcat:pwsedpioz5eovai6vxv3yc6l24

Page 354 of Computational Linguistics Vol. 29, Issue 3 [page]

2003 Computational Linguistics  
The Pearson correlation coefficient r for the lengths will be closer to one when the alignment has succeeded in lining up translated pieces of text, and the p value quantifies the reliability of the correla  ...  The number of aligned nonmarkup text chunks (1) helps characterize the quality of the alignment.  ... 

Two Geometric Algorithms for Layout Analysis [chapter]

Thomas M. Breuel
2002 Lecture Notes in Computer Science  
maximum likelihood matches of geometric text line models in the presence of geometric obstacles.  ...  Reliability of the system is demonstrated on documents from the UW3 database.  ...  Find text lines that respect the columnar structure of the document. 3.  ... 
doi:10.1007/3-540-45869-7_23 fatcat:fnfkl6ftkvgvzh5h2xgxegnboe

Ground-Truth Production in the Transcriptorium Project

Basilis Gatos, Georgios Louloudis, Tim Causer, Kris Grint, Veronica Romero, Joan Andreu Sanchez, Alejandro H. Toselli, Enrique Vidal
2014 2014 11th IAPR International Workshop on Document Analysis Systems  
We also address here a novel low-cost semi-supervised procedure for obtaining pairs of correct line-level aligned detected/extracted text line images and text line transcripts, specially suitable for training  ...  TRANSCRIPTORIUM is a 3-years project that aims to develop innovative, cost-effective solutions for the indexing, search and full transcription of historical handwritten document images, using Handwritten  ...  Text line segmentation Text line segmentation refers to the process of defining the region of every text line on a document image.  ... 
doi:10.1109/das.2014.23 dblp:conf/das/GatosLCGRSTV14 fatcat:szaghjiy3rdf5pzth2aw6oyvtq

Text-line examination for document forgery detection

Joost van Beusekom, Faisal Shafait, Thomas M. Breuel
2012 International Journal on Document Analysis and Recognition  
In questioned document examination, text-line rotation and alignment can be important clues for detecting tampered documents.  ...  In this paper, an approach for forgery detection using text-line information is presented.  ...  Plausibility check using text-line alignment The examination of the alignment property of text-lines has also been previously used in questioned document examination [1] .  ... 
doi:10.1007/s10032-011-0181-5 fatcat:ur75l3tipfd63kd4ntvegup2fy

Presenting documents to clients in Social Work encounters

David Monteiro
2021 Calidoscópio  
clients and how, through talk and bodily conduct, they ensure clients' ability to inspect and make sense of relevant information, managing practical problems concerning clients' access to documents and  ...  Based on a corpus of video recordings of Social Work encounters in Portugal, and taking a multimodal conversation analytical approach, this study examines how social workers present paper documents to  ...  vamos ver / 'let (us) see' (line 5).  ... 
doi:10.4013/cld.2021.192.05 fatcat:pm5umpynnzgurgk4smddg4x5xi

Automatic Line Orientation Measurement for Questioned Document Examination [chapter]

Joost van Beusekom, Faisal Shafait, Thomas Breuel
2009 Lecture Notes in Computer Science  
When experts attempt to identify such forgeries manually, they use among others line orientation as a feature.  ...  This method extracts the text-lines, measures their orientation angle and decides the validity of these measured angles based on previously trained parameters.  ...  It can also be seen that printing text on an existing document may lead to alignments that are neither detectable by this method nor by manual inspection.  ... 
doi:10.1007/978-3-642-03521-0_15 fatcat:stg5cy2c6vdulf2lw2dmnxk36e

Layout-aware text extraction from full-text PDF of scientific articles

Cartic Ramakrishnan, Abhishek Patnia, Eduard Hovy, Gully APC Burns
2012 Source Code for Biology and Medicine  
The Portable Document Format (PDF) is the most commonly used file format for online scientific publications.  ...  We then compared this accuracy with that of the text extracted by the PDF2Text system, 2 commonly used to extract text from PDF.  ...  Figure 4 shows that only 7 out of 86 documents extracted by LA-PDFText (shown using +) produce a poorer alignment score with the Open Access text than PDF2Text (shown using -).  ... 
doi:10.1186/1751-0473-7-7 pmid:22640904 pmcid:PMC3441580 fatcat:jmgj5wso5jbjjhsohxtd4dwram

Automated Parsing of Interlinear Glossed Text from Page Images of Grammatical Descriptions

Erich R. Round, Mark Ellison, Jayden L. Macklin-Cordes, Sacha Beniamine
2020 International Conference on Language Resources and Evaluation  
Typically these sentences are formatted as interlinear glossed text (IGT). Most descriptive grammars, however, exist only as hardcopy or scanned pdf documents.  ...  demonstrate fundamental viability for a technology that can assist in making a large number of linguistic data sources machine readable: the automated identification and parsing of interlinear glossed text  ...  For this reason, we do not focus on alignment in this paper, but rather on the identification of lines of IGT and the functions of those lines as vernacular text, gloss or free translation.  ... 
dblp:conf/lrec/RoundEMB20 fatcat:rp7ofmwuvfgsdnsukovpdxymj4

XY Cut Modular approach for Segmenting pages

Simple Batra
2018 International Journal of Scientific Research in Computer Sciences and Engineering  
In this paper, we propose two separate modules to determining the paragraphs and lines in of a document page which is independent of languages.  ...  the purpose of this experimental research is to present algorithm for reading contents of documented image. Most of the information that is available today in the world is in printed medium.  ...  There are two categories of text line segmentation approaches: searching for (fictitious) separating lines or paths, or searching for aligned physical units.  ... 
doi:10.26438/ijsrcse/v6i2.5156 fatcat:6q24nhgayjfudjv7b7ainb42tu

A Survey of Text Alignment Visualization

Tariq Yousef, Stefan Janicke
2020 IEEE Transactions on Visualization and Computer Graphics  
Text alignment is one of the fundamental techniques text-related domains like natural language processing, computational linguistics, and digital humanities.  ...  On the basis of those tasks, we reviewed existing text alignment visualization approaches, and discuss their advantages and drawbacks.  ...  For instance, iteal uses aligned barcodes to inspect occurring patterns within the whole document, a side-by-side view for line-level alignments in sections, and variant graphs for analyzing word-level  ... 
doi:10.1109/tvcg.2020.3028975 pmid:33044932 fatcat:jxsh4u2clffdjkw4exjeukyp6i

Syntactic regression testing for tree-structured output

Elizabeth Soechting, Kinga Dobolyi, Westley Weimer
2009 2009 11th IEEE International Symposium on Web Systems Evolution  
We model test case outputs that merit human inspection through a set of structural and domainspecific features.  ...  Regression testing is used by software developers to ensure that program modifications have not negatively impacted the correctness of code.  ...  This insight motivates us to find an alignment based on the minimal number of changes that describe the difference between two documents.  ... 
doi:10.1109/wse.2009.5631413 dblp:conf/wse/SoechtingDW09 fatcat:ork5hpmjm5aktedtqqtsdex73u
« Previous Showing results 1 — 15 out of 55,419 results