摘要 |
Disclosed are an image-processing apparatus and method that simply and accurately render an object from an input image, and a program. Face-detection unit (31) detects a face from an input image; mask region setting unit (33) sets a mask region that masks a person in the input image based on a position of the face detected by the face-detection unit (31); background model update unit (51) updates a background image by learning regions other than the masked region in the input image as a background image; and separation unit (54) separates the input image into the background image and a foreground image which is the person region in the input image, based on the background image updated by the background model update unit (51) and the input image. This can be applied, for example, to an image-processing apparatus that renders a person from an input image. |