Scholarlink

The abstract serves as both a general introduction to the issue and a quick, non-technical explanation of the key findings and their consequences. Authors are urged to check that the textile sector is a cornerstone of global manufacturing, considerably contributing to economic development and job creation. This industry is so prominent and has a huge impact on the economy worldwide. This industry still now depended on manual inspections for measuring the checking of the percentage of fabrics. This is crucial work for estimation and quality, which takes so much time and also causes human error. Automation of accurate checking of the percentage of cotton can be beneficial for reducing time and quality assurance. It can speed up manufacturing and reduce expenditure. In this research, we provide a computer vision-based image processing method. Convolutional Neural Networks (CNNs) can analyze images of fabric along with measuring the percentage of cotton from the image of fabric. To justify our model’s effectiveness, we have performed with several CNN models. The accuracy of the VGG 19 model is 97%. This model can predict the percentage of cotton efficiently. The proposed model and solution can make a significant impact on the textile industry by reducing the time of inspection and human error.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

The Prediction of Cotton Percentage from Fabric Image Using Deep Learning

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Sudharam Sur,
  • Shodorson Nath,
  • Angon Bhadra Antu,
  • Shanta Singha,
  • Anik Lal Dey,
  • Mir Ariyan Shuddho,
  • K. M. Safin Kamal,
  • Ahmed Wasif Reza

摘要

The abstract serves as both a general introduction to the issue and a quick, non-technical explanation of the key findings and their consequences. Authors are urged to check that the textile sector is a cornerstone of global manufacturing, considerably contributing to economic development and job creation. This industry is so prominent and has a huge impact on the economy worldwide. This industry still now depended on manual inspections for measuring the checking of the percentage of fabrics. This is crucial work for estimation and quality, which takes so much time and also causes human error. Automation of accurate checking of the percentage of cotton can be beneficial for reducing time and quality assurance. It can speed up manufacturing and reduce expenditure. In this research, we provide a computer vision-based image processing method. Convolutional Neural Networks (CNNs) can analyze images of fabric along with measuring the percentage of cotton from the image of fabric. To justify our model’s effectiveness, we have performed with several CNN models. The accuracy of the VGG 19 model is 97%. This model can predict the percentage of cotton efficiently. The proposed model and solution can make a significant impact on the textile industry by reducing the time of inspection and human error.