Abstract: A testing device includes photographing, segmenting, position determining, and position adjusting units. The photographing unit is configured to photograph a needle tip of a probe needle provided in a probe card used for testing of a test object. The segmenting unit is configured to recognize a needle region and a needle tip region of a validation image photographed by the photographing unit, by inputting the validation image to a segmentation model that is trained as described in the specification. The position determining unit is configured to determine a position of the needle tip based on a positional relationship between the needle region and the needle tip region. The position adjusting unit is configured to adjust a relative position between the test object and the needle tip of the probe needle based on the position of the needle tip determined by the position determining unit.

Abstract: An image processing system includes an interface to which an annotation result on a learning image captured inside a living body is input and a processor including hardware. The processor acquires metadata including difficulty information indicating difficulty of the annotation of the learning image itself, determines reliability information indicating reliability of the annotation result based on the metadata, and outputs a dataset in which the learning image, the annotation result, and the reliability information are associated with each other, as data used in generating a trained model used in inference based on deep learning on an inference target image captured inside a living body.