Segmentation overlapping wear particles with few labelled data and imbalance sample

TL;DR

This paper introduces OWPSNet, a deep learning model combining region segmentation, edge detection, and feature refinement to effectively segment overlapping wear particles in ferrograph images, addressing sample imbalance with a novel loss function.

Contribution

The study proposes a new deep learning framework with a square dice loss function for improved segmentation of overlapped wear particles in ferrograph images.

Findings

OWPSNet effectively segments overlapping wear particles.

Square dice loss improves edge segmentation accuracy.

Model outperforms existing methods on ferrograph dataset.

Abstract

Ferrograph image segmentation is of significance for obtaining features of wear particles. However, wear particles are usually overlapped in the form of debris chains, which makes challenges to segment wear debris. An overlapping wear particle segmentation network (OWPSNet) is proposed in this study to segment the overlapped debris chains. The proposed deep learning model includes three parts: a region segmentation network, an edge detection network and a feature refine module. The region segmentation network is an improved U shape network, and it is applied to separate the wear debris form background of ferrograph image. The edge detection network is used to detect the edges of wear particles. Then, the feature refine module combines low-level features and high-level semantic features to obtain the final results. In order to solve the problem of sample imbalance, we proposed a square dice loss function to optimize the model. Finally, extensive experiments have been carried out on a ferrograph image dataset. Results show that the proposed model is capable of separating overlapping wear particles. Moreover, the proposed square dice loss function can improve the segmentation results, especially for the segmentation results of wear particle edge.