Intelligent automated image clustering for quality assurance

A computer-implemented method comprising:

• receiving data comprising a feed of images corresponding to a plurality of objects passing in front of at least one inspection camera module forming part of an inspection system;
• identifying an optimal image for each object among a plurality of images for such object in the feed of images;
• generating, using a first machine learning model and based on the received data, a representation for each identified optimal image;
• clustering, by one or more second machine learning models, the identified optimal images using the corresponding representations into groups that each correspond to one of a plurality of different object attributes;
• and
• providing access to the groups to a consuming application or process for analysis.

A computer-implemented method comprising:

• receiving data comprising a video feed corresponding to a plurality of objects passing in front of at least one inspection camera module forming part of an inspection system;
• identifying segments of the video feed each corresponding to a different one of the plurality of objects;
• generating, using a first machine learning model and based on the received data, a representation for each identified segment;
• clustering, by one or more second machine learning models, the identified segments using the corresponding representations into groups that each correspond to one of a plurality of different object attributes;
• and
• providing access to the groups to a consuming application or process for analysis.