In an image processing apparatus, a face detection unit 61 detects a face region in a target image. An age recognition unit 62 recognizes the age of a subject based on data of the face region. A similar image search unit 63 searches for data of an existing image having a face region similar to the detected face region as similar image data. A date comparing unit 65, when the age of the subject is confirmed to be within a first range by an age confirmation unit 64, acquires a time difference between the capture dates of the target image data and the similar image data and compares the time difference with a second range. A grouping unit 66, when the time difference is within the second range, classifies the target image data into the same group as the group to which the similar image data belongs.