Industrial product defect detection using custom U-Net

Al Amin, Hongjie Ma, Md. Shazzad Hossain, Nasim Ahmed Roni, Erfanul Haque, S. M. Asaduzzaman, Redwan Abedin, Alif B. Ekram, Rube Farzana Akter

Research output: Chapter in Book/Report/Conference proceedingConference contribution

35 Downloads (Pure)


Numerous automated labour-saving systems have been created and implemented to lower production costs and enhance product quality. Systems for intelligent visual analysis are now playing a more significant role in production lines. Many deep learning and machine learning techniques were previously used to identify defective products. Still, the models were never tested because they did not produce satisfactory results and had numerous other problems adjusting to sparse and poor-quality data. To address this issue, a deep learning-based customised UNet model was introduced in this proposed work. This model was trained on six different classes of data-sets to assess the model’s capability on different image textures and resolutions. The proposed model had an overall accuracy of 97.25%. We also achieved significantly higher precision, recall, and F1 scores of 96.04%, 95.58%, and 96.12%, respectively. The execution times of six different classes can indicate how well a model performs, and the average execution time is only 33.1 seconds, according to observations.
Original languageEnglish
Title of host publication2022 25th International Conference on Computer and Information Technology (ICCIT)
PublisherInstitute of Electrical and Electronics Engineers Inc.
Number of pages6
ISBN (Electronic)9798350346022, 9798350346015
ISBN (Print)9798350346039
Publication statusPublished - 3 Mar 2023
EventIEEE 25th International Conference on Computer and Information Technology (ICCIT) - Long Beach Hotel, Cox’s Bazar, Bangladesh
Duration: 17 Dec 202219 Dec 2022


ConferenceIEEE 25th International Conference on Computer and Information Technology (ICCIT)
CityCox’s Bazar
Internet address


  • defect detection
  • optimised U-Net
  • industrial production mode
  • U-Net 3+
  • convolutional auto-encoder

Cite this