An image processing device estimates a depth of specified tissue included in an object based on an image obtained by capturing the object with light with wavelengths. The image processing device includes: an absorbance calculating unit configured to calculate absorbances at the wavelengths based on pixel values of pixels constituting the image; a component amount estimating unit configured to estimate each of component amounts by using reference spectra at different depths of tissue for each of two or more kinds of light absorbing components contained respectively in two or more kinds of tissue including the specified tissue based on the absorbances; a ratio calculating unit configured to calculate a ratio of component amounts estimated for a light absorbing component contained in at least the specified tissue; and a depth estimating unit configured to estimate at least a depth of the specified tissue in the object based on the ratio.