uu.seUppsala University Publications
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Learning based segmentation and generation methods for handwritten document images
Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Division of Visual Information and Interaction. Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Computerized Image Analysis and Human-Computer Interaction. (Bildanalys och människa-datorinteraktion, Computerized Image Analysis and Human-Computer Interaction)
2019 (English)Doctoral thesis, comprehensive summary (Other academic)
Abstract [en]

Computerized analysis of handwritten documents is an active research area in image analysis and computer vision. The goal is to create tools that can be available for use at university libraries and for researchers in the humanities. Working with large collections of handwritten documents is very time consuming and many old books and letters remain unread for centuries. Efficient computerized methods could help researchers in history, philology and computer linguistics to cost-effectively conduct a whole new type of research based on large collections of documents. The thesis makes a contribution to this area through the development of methods based on machine learning. The passage of time degrades historical documents. Humidity, stains, heat, mold and natural aging of the materials for hundreds of years make the documents increasingly difficult to interpret. The first half of the dissertation is therefore focused on cleaning the visual information in these documents by image segmentation methods based on energy minimization and machine learning. However, machine learning algorithms learn by imitating what is expected of them. One prerequisite for these methods to work is that ground truth is available. This causes a problem for historical documents because there is a shortage of experts who can help to interpret and interpret them. The second part of the thesis is therefore about automatically creating synthetic documents that are similar to handwritten historical documents. Because they are generated from a known text, they have a given facet. The visual content of the generated historical documents includes variation in the writing style and also imitates degradation factors to make the images realistic. When machine learning is trained on synthetic images of handwritten text, with a known facet, in many cases they can even give an even better result for real historical documents.

Place, publisher, year, edition, pages
Uppsala: Acta Universitatis Upsaliensis, 2019. , p. 97
Series
Digital Comprehensive Summaries of Uppsala Dissertations from the Faculty of Science and Technology, ISSN 1651-6214 ; 1783
Keywords [en]
Machine learning, handwriting, handwritten document anlysis, deep learning, image processing
National Category
Computer Systems
Research subject
Computerized Image Processing
Identifiers
URN: urn:nbn:se:uu:diva-379636ISBN: 978-91-513-0599-8 (print)OAI: oai:DiVA.org:uu-379636DiVA, id: diva2:1297042
Public defence
2019-05-08, TLS, Carolina Rediviva Library, Dag Hammarskjölds Väg 1, Uppsala, 09:00 (English)
Opponent
Supervisors
Available from: 2019-04-15 Created: 2019-03-19 Last updated: 2019-06-17Bibliographically approved
List of papers
1. Document binarization using topological clustering guided Laplacian Energy Segmentation
Open this publication in new window or tab >>Document binarization using topological clustering guided Laplacian Energy Segmentation
2014 (English)In: Proceedings International Conference on Frontiers in Handwriting Recognition (ICFHR), 2014, 2014, p. 523-528Conference paper, Published paper (Refereed)
Abstract [en]

The current approach for text binarization proposesa clustering algorithm as a preprocessing stage toan energy-based segmentation method. It uses a clusteringalgorithm to obtain a coarse estimate of the background (BG)and foreground (FG) pixels. These estimates are used as a priorfor the source and sink points of a graph cut implementation,which is used to efficiently find the minimum energy solution ofan objective function to separate the BG and FG. The binaryimage thus obtained is used to refine the edge map that guidesthe graph cut algorithm. A final binary image is obtained byonce again performing the graph cut guided by the refinededges on a Laplacian of the image.

Series
Frontiers in Handwriting Recognition, ISSN 2167-6445 ; 14
Keywords
Image Processing; Classification; Machine Learning; Graph-theoretic methods.
National Category
Computer Systems Signal Processing
Research subject
Computer Science
Identifiers
urn:nbn:se:uu:diva-238316 (URN)10.1109/ICFHR.2014.94 (DOI)978-1-4799-4335-7 (ISBN)
Conference
International Conference on Frontiers in Handwriting Recognition (ICFHR),September 1-4, 2014, Crete, Greece.
Funder
Swedish Research Council, 2012-5743
Available from: 2014-12-11 Created: 2014-12-11 Last updated: 2019-03-19Bibliographically approved
2. Historical document binarization combining semantic labeling and graph cuts
Open this publication in new window or tab >>Historical document binarization combining semantic labeling and graph cuts
2017 (English)In: Image Analysis: Part I, Springer, 2017, p. 386-396Conference paper, Published paper (Refereed)
Abstract [en]

Most data mining applications on collections of historical documents require binarization of the digitized images as a pre-processing step. Historical documents are often subjected to degradations such as parchment aging, smudges and bleed through from the other side. The text is sometimes printed, but more often handwritten. Mathematical modeling of appearance of the text, background and all kinds of degradations, is challenging. In the current work we try to tackle binarization as pixel classification problem. We first apply semantic segmentation, using fully convolutional neural networks. In order to improve the sharpness of the result, we then apply a graph cut algorithm. The labels from the semantic segmentation are used as approximate estimates of the text and background, with the probability map of background used for pruning the edges in the graph cut. The results obtained show significant improvement over the state of the art approach.

Place, publisher, year, edition, pages
Springer, 2017
Series
Lecture Notes in Computer Science, ISSN 0302-9743 ; 10269
National Category
Computer Vision and Robotics (Autonomous Systems)
Research subject
Computerized Image Processing
Identifiers
urn:nbn:se:uu:diva-335335 (URN)10.1007/978-3-319-59126-1_32 (DOI)000454359300032 ()978-3-319-59125-4 (ISBN)
Conference
SCIA 2017, June 12–14, Tromsø, Norway
Funder
Swedish Research Council, 2012-5743Riksbankens Jubileumsfond, NHS14-2068:1
Available from: 2017-05-19 Created: 2017-12-04 Last updated: 2019-03-19Bibliographically approved
3. PDNet: Semantic segmentation integrated with a primal-dual network for document binarization
Open this publication in new window or tab >>PDNet: Semantic segmentation integrated with a primal-dual network for document binarization
2019 (English)In: Pattern Recognition Letters, ISSN 0167-8655, E-ISSN 1872-7344, Vol. 121, p. 52-60Article in journal (Refereed) Published
National Category
Computer Vision and Robotics (Autonomous Systems)
Research subject
Computerized Image Processing
Identifiers
urn:nbn:se:uu:diva-366933 (URN)10.1016/j.patrec.2018.05.011 (DOI)000459876700008 ()
Funder
Swedish Research Council, 2012-5743Riksbankens Jubileumsfond, NHS14-2068:1
Available from: 2018-05-16 Created: 2018-11-27 Last updated: 2019-04-04Bibliographically approved
4. Feature evaluation for handwritten character recognition with regressive and generative Hidden Markov Models
Open this publication in new window or tab >>Feature evaluation for handwritten character recognition with regressive and generative Hidden Markov Models
2016 (English)In: Advances in Visual Computing: Part I, Springer, 2016, p. 278-287Conference paper, Published paper (Refereed)
Place, publisher, year, edition, pages
Springer, 2016
Series
Lecture Notes in Computer Science ; 10072
National Category
Computer Vision and Robotics (Autonomous Systems)
Research subject
Computerized Image Processing
Identifiers
urn:nbn:se:uu:diva-308662 (URN)10.1007/978-3-319-50835-1_26 (DOI)978-3-319-50834-4 (ISBN)
Conference
ISVC 2016, December 12–14, Las Vegas, NV
Projects
q2b – From Quill to Bytes
Available from: 2016-12-10 Created: 2016-11-29 Last updated: 2019-03-19Bibliographically approved
5. CalligraphyNet: Augmenting handwriting generation with quill based stroke width
Open this publication in new window or tab >>CalligraphyNet: Augmenting handwriting generation with quill based stroke width
2019 (English)Manuscript (preprint) (Other academic)
Abstract [en]

Realistic handwritten document generation garners a lot ofinterest from the document research community for its abilityto generate annotated data. In the current approach we haveused GAN-based stroke width enrichment and style transferbased refinement over generated data which result in realisticlooking handwritten document images. The GAN part of dataaugmentation transfers the stroke variation introduced by awriting instrument onto images rendered from trajectories cre-ated by tracking coordinates along the stylus movement. Thecoordinates from stylus movement are augmented with thelearned stroke width variations during the data augmentationblock. An RNN model is then trained to learn the variationalong the movement of the stylus along with the stroke varia-tions corresponding to an input sequence of characters. Thismodel is then used to generate images of words or sentencesgiven an input character string. A document image thus cre-ated is used as a mask to transfer the style variations of the inkand the parchment. The generated image can capture the colorcontent of the ink and parchment useful for creating annotated data.

National Category
Computer Systems
Research subject
Computerized Image Processing
Identifiers
urn:nbn:se:uu:diva-379633 (URN)
Conference
26th IEEE International Conference on Image Processing
Note

Currently under review

Available from: 2019-03-19 Created: 2019-03-19 Last updated: 2019-04-08

Open Access in DiVA

fulltext(2990 kB)142 downloads
File information
File name FULLTEXT01.pdfFile size 2990 kBChecksum SHA-512
9a65355f9cdb468e9cd5c7bff804c2c8a6cdaac5249d00aa8227954897cb5a92d58b41ab4ccc1005239f58c87f4a18f34f2926af7a95e7e3ed3c7aa2b4805915
Type fulltextMimetype application/pdf
Buy this publication >>

Authority records BETA

Ayyalasomayajula, Kalyan Ram

Search in DiVA

By author/editor
Ayyalasomayajula, Kalyan Ram
By organisation
Division of Visual Information and InteractionComputerized Image Analysis and Human-Computer Interaction
Computer Systems

Search outside of DiVA

GoogleGoogle Scholar
Total: 142 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

isbn
urn-nbn

Altmetric score

isbn
urn-nbn
Total: 434 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf