Ändra sökning
RefereraExporteraLänk till posten
Permanent länk

Direktlänk
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annat format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annat språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf
Interpreting the Script: Image Analysis and Machine Learning for Quantitative Studies of Pre-modern Manuscripts
Uppsala universitet, Teknisk-naturvetenskapliga vetenskapsområdet, Matematisk-datavetenskapliga sektionen, Institutionen för informationsteknologi, Avdelningen för visuell information och interaktion. Uppsala universitet, Teknisk-naturvetenskapliga vetenskapsområdet, Matematisk-datavetenskapliga sektionen, Institutionen för informationsteknologi, Bildanalys och människa-datorinteraktion. (q2b)
2017 (Engelska)Doktorsavhandling, sammanläggning (Övrigt vetenskapligt)
Abstract [en]

The humanities have for a long time been a collection of fields that have not gained from the advancements in computational power, as predicted by Moore´s law.  Fields like medicine, biology, physics, chemistry, geology and economics have all developed quantitative tools that take advantage of the exponential increase of processing power over time.  Recent advances in computerized pattern recognition, in combination with a rapid digitization of historical document collections around the world, is about to change this.

The first part of this dissertation focuses on constructing a full system for finding handwritten words in historical manuscripts. A novel segmentation algorithm is presented, capable of finding and separating text lines in pre-modern manuscripts.  Text recognition is performed by translating the image data of the text lines into sequences of numbers, called features. Commonly used features are analysed and evaluated on manuscript sources from the Uppsala University library Carolina Rediviva and the US Library of Congress.  Decoding the text in the vast number of photographed manuscripts from our libraries makes computational linguistics and social network analysis directly applicable to historical sources. Hence, text recognition is considered a key technology for the future of computerized research methods in the humanities.

The second part of this thesis addresses digital palaeography, using a computers superior capacity for endlessly performing measurements on ink stroke shapes. Objective criteria of character shapes only partly catches what a palaeographer use for assessing similarity. The palaeographer often gets a feel for the scribe's style.  This is, however, hard to quantify.  A method for identifying the scribal hands of a pre-modern copy of the revelations of saint Bridget of Sweden, using semi-supervised learning, is presented.  Methods for production year estimation are presented and evaluated on a collection with close to 11000 medieval charters.  The production dates are estimated using a Gaussian process, where the uncertainty is inferred together with the most likely production year.

In summary, this dissertation presents several novel methods related to image analysis and machine learning. In combination with recent advances of the field, they enable efficient computational analysis of very large collections of historical documents.

Ort, förlag, år, upplaga, sidor
Uppsala: Acta Universitatis Upsaliensis, 2017. , s. 95
Serie
Digital Comprehensive Summaries of Uppsala Dissertations from the Faculty of Science and Technology, ISSN 1651-6214 ; 1475
Nyckelord [en]
document analysis, machine learning, image analysis, digital humanities, document dating, writer identification, text recognition
Nationell ämneskategori
Datorseende och robotik (autonoma system)
Forskningsämne
Datavetenskap
Identifikatorer
URN: urn:nbn:se:uu:diva-314211ISBN: 978-91-554-9814-6 (tryckt)OAI: oai:DiVA.org:uu-314211DiVA, id: diva2:1071556
Disputation
2017-03-24, Tidskriftläsesalen, Carolina rediviva, Dag Hammarskjölds väg 1, Uppsala, 10:15 (Engelska)
Opponent
Handledare
Projekt
q2bTillgänglig från: 2017-03-02 Skapad: 2017-01-31 Senast uppdaterad: 2018-01-13
Delarbeten
1. Data Mining Medieval Documents by Word Spotting
Öppna denna publikation i ny flik eller fönster >>Data Mining Medieval Documents by Word Spotting
2011 (Engelska)Ingår i: Proceedings of the 2011 Workshop on Historical Document Imaging and Processing, New York: ACM , 2011, s. 75-82Konferensbidrag, Publicerat paper (Refereegranskat)
Abstract [en]

This paper presents novel results for word spotting based on dynamic time warping applied to medieval manuscripts in Latin and Old Swedish. A target word is marked by a user, and the method automatically finds similar word forms in the document by matching them against the target. The method automatically identifies pages and lines. We show that our method improves accuracy compared to earlier proposals for this kind of handwriting. An advantage of the new method is that it performs matching within a text line without presupposing that the difficult problem of segmenting the text line into individual words has been solved. We evaluate our word spotting implementation on two medieval manuscripts representing two script types. We also show that it can be useful by helping a user find words in a manuscript and present graphs of word statistics as a function of page number.

Ort, förlag, år, upplaga, sidor
New York: ACM, 2011
Nationell ämneskategori
Humaniora och konst Naturvetenskap Språkteknologi (språkvetenskaplig databehandling)
Forskningsämne
Datorlingvistik; Datoriserad bildbehandling
Identifikatorer
urn:nbn:se:uu:diva-162428 (URN)10.1145/2037342.2037355 (DOI)978-1-4503-0916-5 (ISBN)
Konferens
Workshop on Historical Document Imaging and Processing, 16-17 Sep 2011, Beijing, China
Tillgänglig från: 2011-11-30 Skapad: 2011-11-30 Senast uppdaterad: 2018-01-12Bibliografiskt granskad
2. Graph Based Line Segmentation on Cluttered Handwritten Manuscripts
Öppna denna publikation i ny flik eller fönster >>Graph Based Line Segmentation on Cluttered Handwritten Manuscripts
2012 (Engelska)Ingår i: Proceedings of the 21st International Conference on Pattern Recognition, 2012, IEEE , 2012, s. 1570-1573Konferensbidrag, Publicerat paper (Refereegranskat)
Abstract [en]

We propose a two phase line segmentationmethod for handwritten pre-modern densely writ-ten manuscripts. The proposed method combinesthe robustness of projection based methods withthe flexibility of graph based methods. The resultare cut-outs of the image containing each text line.Overlapping characters, help lines and degradationcan create foreground elements spanning several linesthat are hard to separate. We treat the problem offinding a cut through the text line separation as agraph optimization problem, which allows for flexibleseparation of entangled components.The proposed method has been tested on two me-dieval sources with satisfying results. A comparison tosimilar methods, using standard metrics, is presented.

Ort, förlag, år, upplaga, sidor
IEEE, 2012
Nationell ämneskategori
Datorseende och robotik (autonoma system)
Identifikatorer
urn:nbn:se:uu:diva-188588 (URN)978-1-4673-2216-4 (ISBN)
Konferens
21st International Conference on Pattern Recognition (ICPR), 2012
Tillgänglig från: 2012-12-17 Skapad: 2012-12-17 Senast uppdaterad: 2018-01-11Bibliografiskt granskad
3. Feature Weight Optimization and Pruning in Historical Text Recognition
Öppna denna publikation i ny flik eller fönster >>Feature Weight Optimization and Pruning in Historical Text Recognition
2013 (Engelska)Ingår i: Advances of Visual Computing: 9th International Symposium, ISVC 2013, Rethymnon, Crete, Greece, July 29-31, 2013. Proceedings, Part II / [ed] George Bebis, Springer Berlin/Heidelberg, 2013, s. 98-107Konferensbidrag, Publicerat paper (Refereegranskat)
Abstract [en]

In handwritten text recognition, "sliding window" feature extraction represent the visual information contained in written text as feature vector sequences. In this paper, we explore the parameter space of feature weights in search for optimal weights and feature selection using the coordinate descent method. We report a gain of about 5% AUC performance. We use a public dataset for evaluation and also discuss the effects and limitations of "word pruning," a technique in word spotting that is commonly used to boost performance and save computational time.

Ort, förlag, år, upplaga, sidor
Springer Berlin/Heidelberg, 2013
Serie
Lecture Notes in Computer Science, ISSN 0302-9743 ; 8034
Nyckelord
handwritten text recognition
Nationell ämneskategori
Datorseende och robotik (autonoma system)
Forskningsämne
Datoriserad bildanalys; Datoriserad bildbehandling
Identifikatorer
urn:nbn:se:uu:diva-212536 (URN)10.1007/978-3-642-41939-3_10 (DOI)000335169000010 ()978-3-642-41939-3 (ISBN)978-3-642-41938-6 (ISBN)
Konferens
9th International Symposium, ISVC 2013, July 29-31, 2013, Rethymnon, Crete, Greece
Projekt
From Quill to Bytesq2bq2b_vr2012
Forskningsfinansiär
Vetenskapsrådet, 2012-5743
Tillgänglig från: 2013-12-11 Skapad: 2013-12-11 Senast uppdaterad: 2018-01-11Bibliografiskt granskad
4. Feature space denoising improves word spotting
Öppna denna publikation i ny flik eller fönster >>Feature space denoising improves word spotting
2013 (Engelska)Ingår i: Proc. 2nd International Workshop on Historical Document Imaging and Processing, New York: ACM Press, 2013, s. 59-66Konferensbidrag, Publicerat paper (Refereegranskat)
Abstract [en]

Some of the sliding window features commonly used in off-line handwritten text recognition are inherently noisy or sen-sitive to image noise. In this paper, we investigate the ef-fects of several de-noising filters applied in the feature spaceand not in the image domain. The purpose is to target theintrinsic noise of these features, stemming from the com-plex shapes of handwritten characters. This noise is presenteven if the image has been captured without any kind ofartefacts or noise. An evaluation, using a public database,is presented showing that the recognition of word-spottingcan be improved considerably by using de-noising filters inthe feature space.

Ort, förlag, år, upplaga, sidor
New York: ACM Press, 2013
Nyckelord
OCR, handwritten text recognition, filtering
Nationell ämneskategori
Datorseende och robotik (autonoma system)
Forskningsämne
Datoriserad bildbehandling
Identifikatorer
urn:nbn:se:uu:diva-206930 (URN)10.1145/2501115.2501118 (DOI)978-1-4503-2115-0 (ISBN)
Konferens
2nd International Workshop on Historical Document Imaging and Processing
Projekt
q2bq2b_vr2012
Forskningsfinansiär
Vetenskapsrådet, 2012-5743
Tillgänglig från: 2013-09-06 Skapad: 2013-09-06 Senast uppdaterad: 2018-01-11Bibliografiskt granskad
5. Spotting words in medieval manuscripts
Öppna denna publikation i ny flik eller fönster >>Spotting words in medieval manuscripts
2014 (Engelska)Ingår i: Studia Neophilologica, ISSN 0039-3274, E-ISSN 1651-2308, Vol. 86, s. 171-186Artikel i tidskrift (Refereegranskat) Published
Abstract [en]

This article discusses the technology of handwritten text recognition (HTR) as a tool for the analysis of historical handwritten documents. We give a broad overview of this field of research, but the focus is on the use of a method called word spotting' for finding words directly and automatically in scanned images of manuscript pages. We illustrate and evaluate this method by applying it to a medieval manuscript. Word spotting uses digital image analysis to represent stretches of writing as sequences of numerical features. These are intended to capture the linguistically significant aspects of the visual shape of the writing. Two potential words can then be compared mathematically and their degree of similarity assigned a value. Our version of this method gives a false positive rate of about 30%, when the true positive rate is close to 100%, for an application where we search for very frequent short words in a 16th-Century Old Swedish cursiva recentior manuscript. Word spotting would be of use e.g. to researchers who want to explore the content of manuscripts when editions or other transcriptions are unavailable.

Nationell ämneskategori
Data- och informationsvetenskap Jämförande språkvetenskap och allmän lingvistik Språkteknologi (språkvetenskaplig databehandling)
Forskningsämne
Datorlingvistik
Identifikatorer
urn:nbn:se:uu:diva-227725 (URN)10.1080/00393274.2013.871975 (DOI)000335850200012 ()
Tillgänglig från: 2014-01-20 Skapad: 2014-06-30 Senast uppdaterad: 2018-01-11Bibliografiskt granskad
6. Scribal Attribution using a Novel 3-D Quill-Curvature Feature Histogram
Öppna denna publikation i ny flik eller fönster >>Scribal Attribution using a Novel 3-D Quill-Curvature Feature Histogram
2014 (Engelska)Ingår i: Proceedings International Conference on Frontiers in Handwriting Recognition (ICFHR), 2014, 2014Konferensbidrag, Publicerat paper (Refereegranskat)
Abstract [en]

In this paper, we propose a novel pipeline forautomated scribal attribution based on the Quill feature: 1) Wecompensate the Quill feature histogram for pen changes andpage warping. 2) We add curvature as a third dimension in thefeature histogram, to better separate characteristics like loopsand lines. 3) We also investigate the use of several dissimilaritymeasures between the feature histograms. 4) We propose andevaluate semi-supervised learning for classification, to reducethe need of labeled samples.Our evaluation is performed on 1104 pages from a 15thcentury Swedish manuscript. It was chosen because it repre-sents a significant part of Swedish manuscripts of said period.Our results show that only a few percent of the materialneed labelling for average precisions above 95%. Our novelcurvature and registration extensions, together with semi-supervised learning, outperformed the current Quill feature.

Nyckelord
writer identification; semi-supervised learning; classification; historical manuscripts
Nationell ämneskategori
Datavetenskap (datalogi)
Forskningsämne
Datavetenskap; Datoriserad bildbehandling
Identifikatorer
urn:nbn:se:uu:diva-238270 (URN)
Konferens
The International Conference on Frontiers in Handwriting Recognition (ICFHR), September 1-4, 2014, Crete, Greece
Projekt
q2bq2b_vr2012
Forskningsfinansiär
Vetenskapsrådet, 2012-5743
Tillgänglig från: 2014-12-11 Skapad: 2014-12-11 Senast uppdaterad: 2018-05-03Bibliografiskt granskad
7. Large scale style based dating of medieval manuscripts
Öppna denna publikation i ny flik eller fönster >>Large scale style based dating of medieval manuscripts
2015 (Engelska)Ingår i: Proc. 3rd International Workshop on Historical Document Imaging and Processing, New York: ACM Press, 2015, s. 107-114Konferensbidrag, Publicerat paper (Refereegranskat)
Ort, förlag, år, upplaga, sidor
New York: ACM Press, 2015
Nationell ämneskategori
Datorseende och robotik (autonoma system)
Forskningsämne
Datoriserad bildbehandling
Identifikatorer
urn:nbn:se:uu:diva-261747 (URN)10.1145/2809544.2809560 (DOI)978-1-4503-3602-4 (ISBN)
Konferens
HIP 2015, August 22, Nancy, France
Tillgänglig från: 2015-08-22 Skapad: 2015-09-03 Senast uppdaterad: 2018-06-19Bibliografiskt granskad
8. Large scale continuous dating of medieval scribes using a combined image and language model
Öppna denna publikation i ny flik eller fönster >>Large scale continuous dating of medieval scribes using a combined image and language model
2016 (Engelska)Konferensbidrag, Publicerat paper (Refereegranskat)
Abstract [en]

Finding the production date of a pre-modern manuscript is commonly a long process in historical research, requiring days of work from highly specialised experts. In this paper, we present an automatic dating method based on modelling both the language and the image data. By creating a statistical model over the changes in the pen strokes and short character sequences in the transcribed text, a combination of multiple estimators give a distribution over the time line for each manuscript. We have evaluated our estimation scheme on the medieval charter collection "Svenskt Diplomatariums huvudkartotek" (SDHK), including more than 5300 transcribed charters from the period 1135 - 1509. Our system is capable of achieving a median absolute error of 12 years, where the only human input is a transcription of the charter text. Since reading and transcribing the text is a skill that many researchers and students have, compared to the more specialized skill of dating medieval manuscripts based on palaeographical expertise, we find our novel approach suitable for helping individual researchers to date collections of manuscript pages. For larger collections, transcriptions could also be collected using crowd sourcing.

Nationell ämneskategori
Datorseende och robotik (autonoma system)
Forskningsämne
Datoriserad bildbehandling
Identifikatorer
urn:nbn:se:uu:diva-294882 (URN)10.1109/DAS.2016.71 (DOI)000390411200009 ()
Konferens
12th IAPR International Workshop on Document Analysis Systems (DAS), APR 11-14, 2016, Greece
Projekt
q2bq2b_vr2012
Forskningsfinansiär
Vetenskapsrådet, 2012-5743
Tillgänglig från: 2016-05-30 Skapad: 2016-05-30 Senast uppdaterad: 2018-05-04Bibliografiskt granskad
9. Historical Manuscript Production Date Estimation using Deep Convolutional Neural Networks
Öppna denna publikation i ny flik eller fönster >>Historical Manuscript Production Date Estimation using Deep Convolutional Neural Networks
2016 (Engelska)Konferensbidrag, Publicerat paper (Refereegranskat)
Abstract [en]

Deep learning has thus far not been used for dating of pre-modern handwritten documents. In this paper, we propose ways of using deep convolutional neural networks (CNNs) to estimate production dates for such manuscripts. In our approach, a CNN can either be used directly for estimating the production date or as a feature learning framework for other regression techniques. We explore the feature learning approach using Gaussian Processes regression and Support Vector Regression.The evaluation is performed on a unique large dataset of over 10000 medieval charters from the Swedish collection Svenskt Diplomatariums huvudkartotek (SDHK). We show that deep learning is applicable to the task of dating documents and that the performance is on average comparable to that of a human expert.

Ort, förlag, år, upplaga, sidor
IEEE, 2016
Serie
International Conference on Handwriting Recognition, ISSN 2167-6445
Nyckelord
Document analysis, Manuscripts, Document dating, Digital Humanities
Nationell ämneskategori
Datorseende och robotik (autonoma system)
Forskningsämne
Datoriserad bildbehandling
Identifikatorer
urn:nbn:se:uu:diva-306685 (URN)10.1109/ICFHR.2016.114 (DOI)000400052400039 ()978-1-5090-0981-7 (ISBN)
Konferens
International Conference on Frontiers in Handwriting Recognition (ICFHR), October 23-26, 2016, Shenzhen, China.
Projekt
q2bq2b_vr2012
Forskningsfinansiär
Vetenskapsrådet, 2012-5743Riksbankens Jubileumsfond, NHS14-2068:1
Tillgänglig från: 2016-11-01 Skapad: 2016-11-01 Senast uppdaterad: 2019-04-08

Open Access i DiVA

fulltext(2033 kB)347 nedladdningar
Filinformation
Filnamn FULLTEXT01.pdfFilstorlek 2033 kBChecksumma SHA-512
d8e067bdf27dc425f94f4608c78d9a3e6bf7cbbcd5b8d9073b4498b3e3a4af9586b3e2829114ef23fbe88d5f5436d734b4d52ebe43dd79d1f4876242835e4b9d
Typ fulltextMimetyp application/pdf
Köp publikationen >>

Sök vidare i DiVA

Av författaren/redaktören
Wahlberg, Fredrik
Av organisationen
Avdelningen för visuell information och interaktionBildanalys och människa-datorinteraktion
Datorseende och robotik (autonoma system)

Sök vidare utanför DiVA

GoogleGoogle Scholar
Totalt: 347 nedladdningar
Antalet nedladdningar är summan av nedladdningar för alla fulltexter. Det kan inkludera t.ex tidigare versioner som nu inte längre är tillgängliga.

isbn
urn-nbn

Altmetricpoäng

isbn
urn-nbn
Totalt: 3510 träffar
RefereraExporteraLänk till posten
Permanent länk

Direktlänk
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annat format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annat språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf