Application of clustering methods to anomaly detection in fibrous media

International Workshop "Advanced Technologies in Material Science, Mechanical and Automation Engineering – MIP: Engineering – 2019"

材料科学;机械制造;原子能学

Dresvyanskiy, Denis^1 ; Karaseva, Tatiana^1 ; Mitrofanov, Sergei^1 ; Redenbach, Claudia^2 ; Schwaar, Stefanie^3 ; Makogin, Vitalii^4 ; Spodarev, Evgeny^4

Reshetnev Siberian State University of Science and Technology, 31, Krasnoyarsky Rabochy Av., Krasnoyarsk

660037, Russia^1

Technische Universität Kaiserlautern, Fachbereich Mathematik, Postfach 3049, Kaiserslautern

67653, Germany^2

Fraunhofer Institute for Industrial Mathematics ITWM, Fraunhofer-Platz 1, Kaiserslautern

67663, Germany^3

Institut Für Stochastik, Universität Ulm, Ulm

D-89069, Germany^4

关键词: Adaptive weights;    Clustering attributes;    Clustering methods;    Directional entropy;    Expectation-maximisation;    Grey scale images;    Simulated images;    Spatial stochastic;   

Others  :  https://iopscience.iop.org/article/10.1088/1757-899X/537/2/022001/pdf
DOI  :  10.1088/1757-899X/537/2/022001

学科分类：材料科学（综合）

来源: IOP

【 摘 要 】

The paper considers the problem of anomaly detection in 3D images of fibre materials. The spatial Stochastic Expectation Maximisation algorithm and Adaptive Weights Clustering are applied to solve this problem. The initial 3D grey scale image was divided into small cubes subject to clustering. For each cube clustering attributes values were calculated: mean local direction and directional entropy. Clustering is conducted according to the given attributes. The proposed methods are tested on the simulated images and on real fibre materials. The spatial Stochastic Expectation Maximization algorithm shows its effectiveness in comparison to Adaptive Weights Clustering.