Title: Performance assessment of multi-level image thresholding for paper quality inspection

Authors: Valentina Caldarelli; Luca Ceccarelli; Francesco Bianconi; Stefano A. Saetta; Antonio Fernández

Addresses: Department of Engineering, Università degli Studi di Perugia, Via G. Duranti, 93 – 06125 Perugia, Italy ' Department of Engineering, Università degli Studi di Perugia, Via G. Duranti, 93 – 06125 Perugia, Italy ' Department of Engineering, Università degli Studi di Perugia, Via G. Duranti, 93 – 06125 Perugia, Italy ' Department of Engineering, Università degli Studi di Perugia, Via G. Duranti, 93 – 06125 Perugia, Italy ' Department of Engineering Design, Universidade de Vigo, Campus Universitario – 36310 Vigo, Spain

Abstract: Automatic characterisation and detection of dirt particles in pulp and paper plays a pivotal role in the papermaking industry. Machine vision provides many potential advantages in terms of speed, accuracy and repeatability. Such systems make use of image processing algorithms which aim at separating paper and pulp impurities from the background. The most common approach is based on image thresholding, which consists of determining a set of intensity values that split an image into one or more classes, each representing either the background (i.e., an area with no defects) or an area with some types of contraries. In this paper, we present a quantitative experimental evaluation of four image thresholding methods (i.e., Otsu's, Kapur's, Kittler's and Yen's) for dirt analysis in paper. The results show that Kittler's method is the most stable and reliable for this task.

Keywords: machine vision; image thresholding; performance evaluation; paper quality inspection; defect detection; dirt particles; pulp and paper industry; image processing; paper impurities; dirt analysis.

DOI: 10.1504/IJSCOM.2014.066488

International Journal of Service and Computing Oriented Manufacturing, 2014 Vol.1 No.4, pp.281 - 294

Received: 18 Jan 2014
Accepted: 21 Jul 2014
Published online: 31 Dec 2014 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article