Application of Communication Computational Intelligence and Learning

Jadhav, Sangeeta; Desai, Rahul; Sapkal, Ashwini

doi:10.1201/9781003340867

Cited by 2 publications

(1 citation statement)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For years, the textile industry has employed various imaging technologies for quality control, inspection purposes, and defects detection [1]- [3]. These defects can be automatically detected using image processing and computer vision algorithms, ensuring that only high-quality materials are used in the production process and improving the overall quality of the final product.…”

Section: Introductionmentioning

confidence: 99%

Restoration of Textile Yarn Distorted Low-Resolution Micro Computed Tomography Cross Section Images: A MATLAB Restoration Algorithm

ABDELKADER,

PETRIK

2023

NANOCON Conference Proeedings

View full text Add to dashboard Cite

Textile yarn is a group of twisted fibers with diameters of a few micrometers, requiring a nano-resolution scanner to capture precise details of the single fibers perfectly to make a digital twine of the scanned yarn. Computed tomography (CT) technology can 3D digitally scan the sample and achieve a digital twin. The fine fibers' diameter requires a nano-CT to achieve a high-resolution yarn's digital twin; nano-CTs are more expensive than micro-CTs and require about eight times the scanning time compared to micro-CTs, which means more computational power to reconstruct and analyze the scanned objects. This paper introduces a systematic MATLAB algorithm to regenerate distorted yarn's micro-CT low-resolution cross-section images. The algorithm segments the distorted images' fibers, identifies them, and regenerates the clean, highresolution fibers. The algorithm performance is compared to the optical microscopic cross-section image measurements using ImageJ. The results revealed that before processing, the mean fiber diameter measured 9.60 ± 0.78 µm, while post-processing it measured 10.33 ± 0.49 µm. Notably, the algorithm effectively decreased the dispersion of fiber diameters around the mean by 40%, maintaining a diameter close to the design diameter of the fibers of 10 µm.

show abstract

Section: Introductionmentioning

confidence: 99%