Performance assessment of multi-level image thresholding for paper quality inspection. (23rd December 2014)

• Record Type: Journal Article
• Authors: Caldarelli, Valentina; Ceccarelli, Luca; Bianconi, Francesco; Saetta, Stefano A.; Fernández, Antonio
• Is Part Of: International journal of service and computing oriented manufacturing. Volume 1:Number 4(2014)
• Page Start: 281
• Page End: 294
• Publication Date: 2014-12-23
• Subjects: machine vision -- image thresholding -- paper -- defect detection; Computer integrated manufacturing systems -- Periodicals; Manufacturing industries -- Information technology -- Periodicals; Manufacturing industries -- Computer networks -- Periodicals; Service-oriented architecture (Computer science) -- Periodicals; 670.285
• Languages: English
• ISSNs: 2045-175X

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.