Composite material defect segmentation using deep learning models and infrared thermography

Date published

2025-02-20

Free to read from

2025-03-14

Supervisor/s

Journal Title

Journal ISSN

Volume Title

Publisher

Universidade Federal do Rio Grande do Sul

Department

Type

Article

ISSN

0103-4308

Format

Citation

Garcia Vargas I, Fernandes H. (2025) Composite material defect segmentation using deep learning models and infrared thermography. Revista de Informática Teórica e Aplicada, Volume 32, Issue 1, February 2025, pp. 40-46

Abstract

For non-destructive assessment, the segmentation of infrared thermographic images of carbon fiber composites is a critical task in material characterization and quality assessment. This study focuses on applying image processing techniques, particularly adaptive thresholding, alongside neural network models such as U-Net and DeepLabv3 for infrared image segmentation tasks. An experimental analysis was conducted on these networks to compare their performance in segmenting artificial defects from infrared images of a carbon-fibre reinforced polymer sample. The performance of these models was evaluated based on the F1-Score and Intersection over Union (IoU) metrics. The findings reveal that DeepLabv3 demonstrates superior results and efficiency in segmenting patterns of infrared images, achieving an F1-Score of 0.94 and an IoU of 0.74, showcasing its potential for advanced material analysis and quality control.

Description

Software Description

Software Language

Github

Keywords

46 Information and Computing Sciences, 40 Engineering, 4016 Materials Engineering, Networking and Information Technology R&D (NITRD), Machine Learning and Artificial Intelligence

DOI

Rights

Attribution-NonCommercial-NoDerivatives 4.0 International

Relationships

Relationships

Resources

Funder/s

This study was financed in part by the Coordenacao de Aper-feicoamento de Pessoal de Nivel Superior – Brasil (CAPES) –Finance Code 001 and by the National Council for Scientificand Technological Development - Brazil (CNPq) – Finance Codes 407140/2021-2 and 312530/2023-4.