An image processing system includes: a background-image generation unit configured to generate an background image based on input images captured at a plurality of times; a static-area determination unit configured to detect a continued-presence area in a partial area in which an image of a plurality of persons possibly exists in an input image, based on a difference between a first background image generated based on input images captured within a first time width from a processing time and a second background image generated based on input images captured within a second time width from the processing time; a person detection unit configured to detect at least one person which exists in the partial area; and a gathering-score calculation unit configured to detect, based on a detection result of the continued-presence area and a person detection result, continued presence of the plurality of persons in the partial area.