Automated counting and characterization of dirt particles in pulp

  • Authors:

  • Maryam Panjeh Fouladgaran;Aki Mankki;Lasse Lensu;Jari Käyhkö;Heikki Kälviäinen

  • Affiliations:

  • Machine Vision and Pattern Recognition Laboratory, Department of Information Technology, Lappeenranta University of Technology, Finland, Lappeenranta, Finland;FiberLaboratory, Department of Chemical Technology, Lappeenranta University of Technology, Finland, Lappeenranta, Finland;Machine Vision and Pattern Recognition Laboratory, Department of Information Technology, Lappeenranta University of Technology, Finland, Lappeenranta, Finland;FiberLaboratory, Department of Chemical Technology, Lappeenranta University of Technology, Finland, Lappeenranta, Finland;Machine Vision and Pattern Recognition Laboratory, Department of Information Technology, Lappeenranta University of Technology, Finland, Lappeenranta, Finland

  • Venue:
  • ICCVG'10 Proceedings of the 2010 international conference on Computer vision and graphics: Part II
  • Year:
  • 2010

Quantified Score

Hi-index 0.00

Visualization

Abstract

Dirt count and dirt particle characterization have an important role in the quality control of the pulp and paper production. The precision of the existing image analysis systems is mostly limited by methods for only extracting the dirt particles from the images of pulp samples with non-uniform backgrounds. The goal of this study was to develop a more advanced automated method for the dirt counting and dirt particle classification. For the segmentation of dirt particles, the use of the developed Niblack thresholding method and the Kittler thresholding method was proposed. The methods and different image features for classification were experimentally studied by using a set of pulp sheets. Expert ground truth concerning the dirt count and dirt particle classes was collected to evaluate the performance of the methods. The evaluation results showed the potential of the selected methods for the purpose.