The quality of food products is very important for the human health. The large population and the increased requirements of food products makes it difficult to arrive the desired quality. Sorting tons of fruits and vegetables manually is a slow , costly, and an inaccurate process. In this research a vision-based sorting system is developed to increase the quality of food products. The sorting process depends on capturing the image of the fruit or product and analyzing this image to discard defected products. Signals are send via computer interfacing cards to control sorting gates. Four different systems for different food products have been developed namely, apples , tomatoes, eggs , and lemons. A dataset of 1000 images is used to train and test the vision systems (250 images for each product). An accuracy of 97% with speed up to 200 images/minute has been achieved.