Disclosed herein is an image processing device including: a face detector configured to detect a face from an image given on a basis of detection information; and a processing unit configured to set the detection information of the face detector, receive at least an input image before distortion correction of the image before the distortion correction and an image after the distortion correction, divide an entire image region of the input image, and supply each of the divided images to the face detector on a time-division basis, wherein the face detector detects faces from a face of a maximum size to a face of a minimum size in the entire image in a detectable range.