Scratch Detection on Speaker Surface

csdetb-icono

Customer

An inspection company that inspects various materials using High-end Technologies e.g. Computer Vision and Robotics.

Project Details

  • Duration: 1 Month

Technologies:

  • TensorFlow
  • Python
  • OpenCV
  • Industrial
  • GigE Cameras
  • Flask
problem-img

Problem

They faced multiple problems while finding defects on the “Speaker Net” Surface.

  • Missed Identification as it is Prone to Human errors
  • Low Accuracy using conventional AI models
solution-img

Solution

We have developed a custom AI Segmentation model that not only identifies/detects the scratches but also classifies them according to their nature.

  • High-end Industrial Camera captures the images and sends them to the Edge Processing Device for OCR.
  • This helps in prioritizing the seriousness of the defects and helps further to take decisive actions.

99%

The Model identifies the defects with 99% accuracy.

Insights on innovation

Stay updated with the trending and most impactful tech insights. Check out the expert analyses, real-world applications, and forward-thinking ideas that shape the future of AI Computer Vision and innovation.