Provided is an image processing apparatus including a hand shape recognition unit that performs hand shape recognition on an input image to detect a position and a size of a hand with a specific shape in the input image, a determination region setting unit that sets a region in a vicinity of the hand on the input image as a determination region used to recognize a gesture performed using the hand, based on the position and the size of the hand, and a gesture recognition unit that recognizes the gesture by monitoring movement of the hand to the determination region.