Mango is a leading fruit commodity that is able to increase industrial development and exports in Indonesia. There are 33 species of mangoes spread throughout the territory of the Republic of Indonesia and have many variations of fruit shapes in each type. However, the problem that occurs is the difficulty of information related to data on mango varieties, so to help these problems, the researchers created a digital encyclopedia system that is able to provide information related to the diversity of mango varieties. This encyclopedia can classify and identify 5 types of mangoes, namely Apple Mango, Gedong Gincu Mango, Golek Mango, Manalagi Mango and Gadung Mango. Parameters used to distinguish mango varieties are area, perimeter, eccentricity, major axis length and diameter. The classification method used, namely backpropagation, is able to classify the five mango varieties with a training accuracy of 99.6% and a testing accuracy of 96%.

Keywords - digital encyclopedia; mango varieties; computer vision; shape parameters; backpropagation.