A Hybrid Method for the Segmentation of a Ferrograph Image Using Marker-Controlled Watershed and Grey Clustering. Issue 3 (3rd May 2016)

• Record Type: Journal Article
• Authors: Wang, Jingqiu; Yao, Panpan; Liu, Wanlong; Wang, Xiaolei
• Is Part Of: Tribology transactions. Volume 59:Issue 3(2016)
• Page Start: 513
• Page End: 521
• Publication Date: 2016-05-03
• Subjects: Wear particle analysis -- ferrography -- wear particle segmentation -- marker-controlled watershed -- grey clustering; Tribology -- Periodicals; 621
• DOI: 10.1080/10402004.2015.1091534
• Languages: English
• ISSNs: 1040-2004

Abstract

ABSTRACT: Aimed at the correct segmentation of wear particles in ferrograph images, a new method combining marker-controlled watershed and an improved grey clustering algorithm is proposed in this article. First, the marker-controlled watershed is applied to ferrograph images to efficiently obtain the initial segmentation of wear particles. Then, an improved grey clustering algorithm utilizing color characteristics and relative position information is applied to merge the oversegmented regions after the watershed segmentation. This new algorithm is tested for ferrograph images and the results are compared with those of other algorithms. The experimental results show that the proposed method is effective for the segmentation of large wear particles and fine wear debris deposited as chains on the ferrograph, and it is proven to be a practical method for segmenting wear particles quickly and accurately.