An image processing apparatus estimates obverse and reverse pairs as obverse and reverse images of a plurality of cards even if positions of obverse and reverse images of respective cards shift when a user turns cards upside down to scan reverse images when scanning obverse and reverse images of cards and associating obverse and reverse images of cards with each other as obverse and reverse pairs, and presents estimated pairs to the user. A first image and second image are acquired to extract first and second rectangular images and central coordinate values thereof from acquired first and second images. When the central coordinate value extracted from the acquired second image is located within a predetermined distance from the central coordinate value extracted from the acquired first image, it is discriminated that the first rectangular image and second rectangular image as a combination serving as an obverse and reverse pair.