An image processing device classifies an attention region included in an image into multiple classification items. The image processing device has: an initial region detector (110) that detects at least part of the attention region and sets the part as an initial region an expansion region detector (120, 210) that detects an expansion region by expanding the initial region and a region determining unit (130, 310) that calculates feature data of the initial region and the expansion region, and determines, based on the feature data, to which of the multiple classification items the attention region belongs.
