An image processing device includes: a first generating unit configured to generate, based on a distance image generated from a plurality of taken images imaged by a plurality of imaging units in a travelling direction, and made from distance values corresponding to the travelling direction, a first image indicating a frequency distribution associating actual distances in a direction orthogonal to the travelling direction with the distance values; a second generating unit configured to generate, based on the distance image, a second image indicating a frequency distribution associating a horizontal direction of the distance image with the distance values; a first processing unit configured to detect a face of an object represented by the first image, using at least the first image; and a second processing unit configured to identify a type of the face of the object using at least the second image.