Model selection method and image processing method

A model selection method of selecting at least one machine learning model from among a plurality of machine learning models by using a plurality of confirmation images, the plurality of machine learning models being for performing image processing,

• the model selection method comprising:
• a) a first model selection process of selecting, from among all of the plurality of machine learning models that are included in a total model group, a plurality of machine learning models as a first model group by using a first image group that includes at least one confirmation image among the plurality of confirmation images;
• and
• b) a second model selection process of selecting at least one machine learning model as a second model group from among the plurality of machine learning models included in the first model group, by using a second image group that includes a plurality of confirmation images among the plurality of confirmation images,
• the second model selection process b) being performed after the first model selection process a),
• wherein the number of the plurality of confirmation images included in the second image group is larger than the number of the at least one confirmation image included in the first image group.