An image processing apparatus includes a storage device for storing a position of a predetermined region in an image conforming to a predetermined format, a processor for acquiring an input image including a character recognition target region, cutting out a region corresponding to the character recognition target region from the input image or an image generated from the input image to generate a corrected image in which the region is placed at the position of the predetermined region in the image conforming to the predetermined format, and detecting a character from the corrected image, and an output device for outputting information related to the detected character.