Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{200560,
        author = {Visal J and Dr. Kanchana Rajaram},
        title = {Computer Vision and Deep Learning based Automated Fabric Inspection System},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {13},
        number = {1},
        pages = {983-988},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=200560},
        abstract = {Manual inspection is subjective, inconsistent, and heavily dependent on labour, it continues to be a major bottleneck in the textile industry. In addition to being expensive and time-consuming, manual examination is not productive or scalable. Using three convolutional neural network (CNN) architectures MobileNetV2, ResNet50, Google Net (Inception-v1) this study offers an automated surface and defect classification system based on deep learning. To improve feature variability, a balanced dataset of 136 textile images was pre-processed and enhanced. The proposed method greatly increases prediction speed while retaining performance on par with sophisticated current models, facilitating its use in real-time fabric inspection. In order to lower human error and enhance fabric quality control, the technology exhibits encouraging potential for incorporation into industrial inspection pipelines. Additionally, transfer learning models are used to classify fabric surface types (front and back) and fabric defect kinds (holes, knots, netting numerous, thick bar, thin bar, broken end) in order to determine the type of surface, detect the defect type, and determine whether the fabric has stains. It is observed that GoogLeNet exhibits higher accuracy of 92% for fabric surface type classification and 90% for fabric defect classification, compared to the other models.},
        keywords = {Fabric defect detection, Fabric Surface Type, Defect types, deep learning, computer vision, MobileNetV2, Google Net, Efficient Net, textile inspection, transfer learning.},
        month = {June},
        }