Assessing print quality by machine in offset colour printing

作者：Lundstrom J^*; Verikas A

来源：Knowledge-Based Systems, 2013, 37: 70-79.

DOI：10.1016/j.knosys.2012.07.022

• Random forest
• Variable importance
• t-Stochastic neighbour embedding
• Print quality
• Subjective quality assessment

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.

• 出版日期2013-1