IMAGE CAPTURE METHOD AND IMAGE CAPTURE DEVICE

An image capture method used when inspecting an object using an inspection module including a machine learning model in order to be capable of assisting in optimizing the image capture conditions of the object, said image capture method comprising: illuminating an object having known label data, and capturing images of the object using a plurality of illumination parameters to obtain a plurality of captured images; on the basis of an image data set obtained by associating a captured image with an illumination parameter, generating an estimated image of the object on the assumption that the object is illuminated using the illumination parameter; setting the maximum number of captured images permitted for the object; and performing learning by means of a machine learning model using each integer number of captured images up to and including the maximum number of captured images, optimizing illumination parameters and inspection algorithm parameters on the basis of the result of a comparison between the label data of the object and results of estimation based on the machine learning model, calculating an index representing inspection performance that is expected to be achieved using each integer number of captured images, and presenting each calculated index to a user.