Assessing print quality by machine in offset colour printing

• Published in: Knowledge-based systems Vol. 37; pp. 70 - 79
• Main Authors: Lundström, J., Verikas, A.
• Format: Journal Article
• Language: English
• Published: Elsevier B.V 01-01-2013
• Subjects: Color; Print quality; Random forest; Subjective quality assessment; t-Stochastic neighbour embedding; Variable importance; t-Stochastic neighbour embedding; Random forest; Subjective quality assessment; Variable importance; Print quality
• ISSN: 0950-7051; 1872-7409; 1872-7409
• DOI: 10.1016/j.knosys.2012.07.022

Information processing steps in printing industry are highly automated, except the last one—print quality assessment, which usually is a manual, tedious, and subjective procedure. This article presents a random forests-based technique for automatic print quality assessment based on objective values of several print quality attributes. Values of the attributes are obtained from soft sensors through data mining and colour image analysis. Experimental investigations have shown good correspondence between print quality evaluations obtained by the technique proposed and the average observer.