Publications:Image analysis and artificial neural network for colour classification in multicolour newspaper printing
From ISLAB/CAISR
Title | Image analysis and artificial neural network for colour classification in multicolour newspaper printing |
---|---|
Author | Antanas Verikas and Kerstin Malmqvist and Hans Busk |
Year | 1994 |
PublicationType | Conference Paper |
Journal | |
HostPublication | 1994 International Printing and Graphic Arts Conference : October 17-20, 1994 Chateau Halifax Hotel, Halifax, Canada |
Conference | 1994 International Printing and Graphic Arts Conference, Halifax, Canada, 17-20 October 1994 |
DOI | |
Diva url | http://hh.diva-portal.org/smash/record.jsf?searchId=1&pid=diva2:544669 |
Abstract | Automatic inspection of printed multicoloured screen pictures demands methods for colour classification of screen dots and pans of screen dots directly in an arbitrary picture. The paper describes a technique using colour image analysis and artificial neural network for inverse colour separation. For every arbitrary small part of a coloured picture it is determined which coloured inks that have been printed in that part. Special attention is paid to the problem of seperating between black colour produced by black ink and black colour produced by combining cyan, magenta and yellow ink. The technique is tested on multicoloured newsprint and a high correct colour classification rate has been demonstrated. |