An image processing apparatus includes a first eyes-and-mouth detecting unit to detect eye boundaries and a mouth boundary from a first face image; a second eyes-and-mouth detecting unit to detect eye boundaries and a mouth boundary from a second face image; a first skin model generating unit to generate a first skin model; a second skin model generating unit to generate a second skin model; an inside-of-mouth model generating unit to generate an inside-of-mouth model; an eyeball model generating unit configured to generate an eyeball model; a first deformation parameter generating unit to generate a first deformation parameter; a second deformation parameter generating unit configured to generate a second deformation parameter; and an output unit to output the first and second skin models, the first and second deformation parameters, the inside-of-mouth model, and the eyeball model as animation data.