A cooking apparatus includes: a cooking chamber configured to accommodate an object to be cooked; a camera; and a controller configured to cause the cooking apparatus to: obtain, by the camera, a plurality of images of an inside of the cooking chamber based on the object being accommodated in the cooking chamber and in a cooking process, compare the plurality of images to identify image change for each region, assign a contamination weight to the each region based on the image change, and perform a cleaning process based on completion of the cooking process and the contamination weight, wherein each image of the plurality of images includes a plurality of regions.