An image capturing apparatus includes: a first image capturing unit that captures a subject existing image; a first nonflatness calculating unit that calculates nonflatness of a peripheral portion of the subject existing image; a first determination unit that determines whether the nonflatness of the peripheral portion of the subject existing image is higher than a threshold value; a background generating unit that generates an extracting background image from the peripheral portion of the subject existing image when the first determination unit determines that the nonflatness is not higher than the threshold value, the extracting background image serving to extract a subject region containing the subject in the subject existing image; and a subject extracting unit that extracts the subject region from the subject existing image based on difference information of each corresponding pixel between the extracting background image and the subject existing image.