Application of Clustering Methods to Anomaly Detection in Fibrous Media

TL;DR

This paper explores clustering techniques for detecting anomalies in 3D fibre material images, using stochastic EM and adaptive clustering to analyze local features and identify irregularities.

Contribution

It introduces the application of stochastic EM and adaptive clustering methods to 3D fibre image anomaly detection, focusing on local directional attributes.

Findings

Methods successfully detect anomalies in simulated images.

Clustering based on local direction and entropy is effective.

Approach validated on real fibre material images.

Abstract

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.