Author Login IJIRT Partner Network (IPN) Login

Automated Defects Detection in Manufacturing using Convolutional Neural Networks

  • Unique Paper ID: 167232
  • Volume: 11
  • Issue: 3
  • PageNo: 861-866
  • Abstract:
  • Defects detection in manufacturing is an essential component of industrial production quality control. The combination of image processing and convolutional neural networks (CNNs) has developed as a potent solution to deal with this issue. This paper examines the creation of a reliable system for defect detection in manufacturing, leveraging the power of image processing and CNNs. This novel method analyzes visual data taken during the manufacturing process to find and categorize defects from small imperfections to serious flaws. This system makes use of image preprocessing methods to improve image quality and extract required features. Using the labelled data, convolutional neural networks are trained to accurately diagnose the defects. This approach gives several benefits that include automation, monitoring in real-time, and consistent outcomes which reduce human faults and production downtime. Finally, the combination of image processing and CNNs for defect detection in manufacturing assures to improve product quality with efficiency by curtailing production value and waste.
Download article email to a friend

Cite This Article

  • ISSN: 2349-6002
  • Volume: 11
  • Issue: 3
  • PageNo: 861-866

Automated Defects Detection in Manufacturing using Convolutional Neural Networks

Related Articles

09 Sep, 2024

Multilingual Sign Language Translation System

Read More
Impact Factor
8.01 (Year 2024)
UGC Approved
Journal no 47859

Join Our IPN

IJIRT Partner Network

Submit your research paper and those of your network (friends, colleagues, or peers) through your IPN account, and receive 800 INR for each paper that gets published.

Join Now

Latest Publication

Archive

View More

Recent Conferences

NCSEM 2024

National Conference on Sustainable Engineering and Management - 2024 Last Date: 15th March 2024

Submit inquiry