# Vision-based inspection system employing computer vision & neural networks for detection of fractures in manufactured components

**Authors:** Sarthak J Shetty  
**arXiv:** [1901.08864](https://arxiv.org/abs/1901.08864)  
**Date:** 2019-01-25  
**Summary page:** https://www.summarizepaper.com/en/paper/1901.08864v1/

## Key points

- The need for effective quality-control systems in manufacturing is crucial to ensure high-quality components.
- Vision-based inspection systems have become popular due to advancements in computing power and image processing techniques.
- A recent study by Sarthak J Shetty introduces a novel approach using a vision-based inspection system (VBI) that employs computer vision and neural networks for defect detection.
- The VBI system not only detects defects but also predicts surface fractures and wear using machine learning algorithms.
- Open-source tools like OpenCV for computer vision and Tensorflow for machine learning are leveraged to accurately detect and predict defects in manufactured gears.
- Combining cutting-edge technologies like computer vision and machine learning can enhance quality control processes in manufacturing environments.
- Integrating advanced technologies improves efficiency and accuracy in defect detection, offering valuable insights for industries seeking to enhance their quality assurance processes amidst automation and robotics integration.

## Summary

In the rapidly evolving landscape of automation and robotic integration in manufacturing, the need for effective quality-control systems is paramount to ensure the production of high-quality components. Vision-based inspection systems have emerged as a popular choice among various quality-control methods due to advancements in computing power and image processing techniques. In a recent study by Sarthak J Shetty titled "Vision-based inspection system employing computer vision & neural networks for detection of fractures in manufactured components," a novel approach to quality control is presented. The vision-based inspection system (VBI) not only detects defects in manufactured components but also utilizes machine learning algorithms to predict the presence of surface fractures and wear. By leveraging open-source tools such as OpenCV for computer vision and Tensorflow for machine learning, the VBI system accurately detects and predicts surface defects like fractures in manufactured gears. This innovative approach showcases the potential of combining cutting-edge technologies to enhance quality control processes in manufacturing environments. Overall, this research highlights the importance of integrating advanced technologies like computer vision and machine learning into traditional quality-control systems. It emphasizes how these advancements can improve efficiency and accuracy in detecting defects in manufactured components. The findings offer valuable insights for industries looking to enhance their quality assurance processes amidst the ongoing shift towards automation and robotics integration.