Anthracnose is caused mainly by the fungus Colletotrichum sp. and has became an important disease due to its difficult phytosanitary control in mango crops. Its easy spread through the air and abundant presence in tropical climates, causes the loss of numerous mango crops and thus economic damage to farmers. For this reason, the objective of this study is the development of a system for the detection of anthracnose using hyperspectral images that serves as support to the farmer for its correct diagnosis. For this purpose, classification methods were used, such as LDA and KNN, as well as techniques focused on spectral data such as SAM. As main result, it was found that the system achieves an accuracy greater than 90% for samples obtained from the underside of the leaf and an average of 70% for samples from the upperside. In conclussion, the system showed great potential for its use as a diagnostic tool for anthracnose in mango.