hh.sePublications
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • 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
Unsupervised colour image segmentation applied to printing quality assessment
Halmstad University, School of Information Science, Computer and Electrical Engineering (IDE), Halmstad Embedded and Intelligent Systems Research (EIS).
Halmstad University, School of Information Science, Computer and Electrical Engineering (IDE), Halmstad Embedded and Intelligent Systems Research (EIS).ORCID iD: 0000-0003-2185-8973
Department of Applied Electronics, Kaunas University of Technology.
2005 (English)In: Image and Vision Computing, ISSN 0262-8856, E-ISSN 1872-8138, Vol. 23, no 4, p. 417-425Article in journal (Refereed) Published
Abstract [en]

We present an option for colour image segmentation applied to printing quality assessment in offset lithographic printing by measuring an average ink dot size in halftone pictures. The segmentation is accomplished in two stages through classification of image pixels. In the first stage, rough image segmentation is performed. The results of the first segmentation stage are then utilized to collect a balanced training data set for learning refined parameters of the decision rules. The developed software is successfully used in a printing shop to assess the ink dot size on paper and printing plates.

Place, publisher, year, edition, pages
Amsterdam: Elsevier, 2005. Vol. 23, no 4, p. 417-425
Keywords [en]
Colour image segmentation, Fuzzy clustering, Quality inspection, Colour printing
National Category
Computer Vision and Robotics (Autonomous Systems)
Identifiers
URN: urn:nbn:se:hh:diva-259DOI: 10.1016/j.imavis.2004.11.003ISI: 000227222100005Scopus ID: 2-s2.0-13444278799Local ID: 2082/554OAI: oai:DiVA.org:hh-259DiVA, id: diva2:237438
Available from: 2006-11-24 Created: 2006-11-24 Last updated: 2018-03-23Bibliographically approved
In thesis
1. Using multicoloured halftone screens for offset print quality monitoring
Open this publication in new window or tab >>Using multicoloured halftone screens for offset print quality monitoring
2005 (English)Licentiate thesis, comprehensive summary (Other academic)
Abstract [en]

In the newspaper printing industry, offset is the dominating printing method and the use of multicolour printing has increased rapidly in newspapers during the last decade. The offset printing process relies on the assumption that an uniform film of ink of right thickness is transferred onto the printing areas. The quality of reproduction of colour images in offset printing is dependent on a number of parameters in a chain of steps and in the end it is the amount and the distribution of ink deposited on the substrate that create the sensation and thus the perceived colours. We identify three control points in the offset printing process and present methods for assessing the printing process quality in two of these points:

• Methods for determining if the printing plates carry the correct image

• Methods for determining the amount of ink deposited onto the newsprint

A new concept of colour impression is introduced as a measure of the amount of ink deposited on the newsprint. Two factors contribute to values of the colour impression, the halftone dot-size and ink density. Colour impression values are determined on gray-bars using a CCD-camera based system. Colour impression values can also be determined in an area containing an arbitrary combination of cyan magenta and yellow inks. The correct amount of ink is known either from a reference print or from prepress information. Thus, the deviation of the amount of ink can be determined that can be used as control value by a press operator or as input to a control system.

How a closed loop controller can be designed based on the colour impression values is also shown.

It is demonstrated that the methods developed can be used for off-line print quality monitoring and ink feed control, or preferably in an online system in a newspaper printing press.

Place, publisher, year, edition, pages
Linköping: Linköping University Electronic Press, 2005. p. 48
Series
Linköping studies in science and technology. Licentiate thesis, ISSN 0280-7971 ; 1147
Keywords
Multicolour printing, Printing process, Colour images, Colour impression, CCD-camera
National Category
Computer Engineering
Identifiers
urn:nbn:se:hh:diva-713 (URN)2082/1062 (Local ID)91-85297-25-9 (ISBN)2082/1062 (Archive number)2082/1062 (OAI)
Presentation
2005-02-10, 00:00 (English)
Supervisors
Note

Report code: LiU-TEK-LIC-2005:02

Available from: 2007-06-04 Created: 2007-06-04 Last updated: 2018-03-23Bibliographically approved

Open Access in DiVA

No full text in DiVA

Other links

Publisher's full textScopus

Authority records BETA

Bergman, LarsVerikas, Antanas

Search in DiVA

By author/editor
Bergman, LarsVerikas, Antanas
By organisation
Halmstad Embedded and Intelligent Systems Research (EIS)
In the same journal
Image and Vision Computing
Computer Vision and Robotics (Autonomous Systems)

Search outside of DiVA

GoogleGoogle Scholar

doi
urn-nbn

Altmetric score

doi
urn-nbn
Total: 206 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • 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