tomatoes are commercial commodies that play a major role in Egyptian economy. They are considered one of the major vegetable crops in Egypt because of its nutritional, consumption, processing and export value. They may be harvested at different maturity stages and each maturity stage has its characteristics of quality. On the other hand, acceptance of tomato for eating depends on many factors such as variety, texture, maturity, size, shape etc. In this study, a simple machine vision system was developed for sorting three maturity classes of tomatoes grown in Egypt. For the sorting analysis, three color features L*,a* and b* were extracted from each tomatoes class images. Nine different color features are calculated from the three color features. An artificial neural network classifier with Backpropagation method was tested. The input layer consists of twelve color features, the hidden layer consists of twelve nodes and the output layer consists of three nodes representing three tomatoes classes (green, pink and red). The best sorting accuracies in testing data set are 100%, 92.9% and 100% for green, pink and red classes, respectively. The overall sorting accuracy is 97.9%. Finally, based on the obtained results, a tomato sorting machine can be designed to categorize 3 colors of tomatoes decreasing human labor and to reducing sorting time.