Abstract: An image processing apparatus includes a processor configured to: extract position coordinates of each document image from an entire image resulting from photographing multiple documents; perform a first operation that extracts, from the document images included in the entire image, a first document image having two sides parallel with a direction of arrangement of the documents and having a first side of the two sides being a far side from a first coordinate axis, the first side having the shortest distance to the first coordinate axis, the first coordinate axis being in parallel with the direction of the arrangement of the documents set with respect to an origin of the entire image; perform a second operation that extracts, as an document image of the same group, a second document image overlapping an extension of the first side of the extracted first image document; and perform a third operation that sets a page number on each of the extracted document images of the same group in an order of closeness from