Machine learning-based evaluation of label placement on devices

Abstract

Systems and methods for machine vision-based metrology in automated label placement inspection and quality control are disclosed. An example system can evaluate label placement on an object by applying one or more machine learning (ML) models to an image of the object. The trained ML models are designed to recognize the object and a label on it. Morphological features such as the edges of the object and the label are recognized using the trained ML models, and a spatial metric can be determined using these features. Based on this spatial metric, a label placement indicator can be generated to show that the label passes the quality control check if it is placed within predetermined tolerances on the object.