Earlier this year, Edge Impulse released a powerful new learning block that adds anomaly detection to your visual inspection tasks. Previously, this block only included support for the Gaussian Mixture Model (GMM) scoring function. The application of GMM on the feature maps allows for a nuanced detection of irregularities, providing outputs that include not only the presence of an anomaly but also its specific location within the image.
This is a companion discussion topic for the original entry at https://www.edgeimpulse.com/blog/patchcore-boosts-visual-anomaly-detection-in-edge-impulse