A framework is developed for automation of the card game SET. A SET card has four properties (quantity, color, fill and shape), which each can take three values. The goal is to find special combinations of three cards, of which each individual property is equal or totally different for all three cards. The paper researches how these SETs can automatically be detected from an image using Computer Vision, dealing with three problems sequentially: the locating of cards on the image, the classification of the cards and the finding of SETs amongst the cards.