An image processing device includes: a feature detection image generating unit that generates multiple feature detection images corresponding to multiple classes by applying a convolutional neural network having the classes learned previously to an input image; a post-processing unit that generates a measurement result by performing a post-process on at least some feature detection images of the multiple feature detection images on the basis of a setting parameter; and a user interface unit that receives an input of the setting parameter while presenting a user at least one of at least some of the feature detection images which are generated by the feature detection image generating unit and the measurement result which is generated by causing the post-processing unit to perform the post-process using at least some of the feature detection images which are generated by the feature detection image generating unit.