A method of classifying slices or a portion cut from a food product according to an optical image of the slice. After a slice is removed from a food product loaf the slice is passed into an image field of a digital image receiving device. A control generates a pixel-by-pixel image data of the slice using input from the digital image receiving device. The control calculates a surface area of the slice from the data, and a fat content of the slice on a pixel-by-pixel basis. The fat content data is compared to at least one predetermined limit and the slice is classified accordingly.