Automated Quality Inspection


Manually inspecting micrographs for defects and classifying them is very time consuming and typically costs over £100k per annum.


80% in human operator involvement time saved and thousands of classifications are obtained within 2 hours.

The How

  1. Collate micrographs and data associated with them
  2. Develop Convolutional Neural Network model
  3. Develop a system to classify micrograph images as containing defects or not.
  4. Validate results. Trials showed over 90% accuracy in classifying micrographs