An information processing device performs processing on document image data. The document image data includes first image data of a plurality of images and second image data. The first image data undergoes character recognition processing. The second image data does not undergo character recognition processing. The information processing device includes a detecting section, an extracting section, and a processing section. The detecting section detects the first image data from the document image data. The extracting section extracts the first image data from the document image data. The processing section generates composite image data by compositing the images of the first image data and performs character recognition on the composite image data.