An image processing apparatus includes a document area extracting module configured to extract a document area from the captured image, the document area being an area of the document, a note area extracting module configured to extract a first note area from the captured image, the first note area being an area of the first note positioned at a first position of the document area of the first page, a character determining module configured to determine the first character included in the first note area by optical character recognition, a document image generating module configured to mask the first note area included in the document area, and generate a document image, a file name generating module configured to generate a file name including the first character, and a file generating module configured to generate an electronic file of the document image having the file name.