An image processing apparatus includes an image input that receives input of image data of a captured human being, a region detector that detects a specific color region of the image data, a filter that smooths a pixel value in the specific color region detected by the region detector by using a frame of the image data input into the image input and each of previous and subsequent frames of the image data of the inputting into the image input, a coder that codes an output image of the filter, and an output that outputs the output image of the filter coded by the coder.