This article presents a methodology for the classification of retinal vessels based on agreement technologies and artificial vision. Some studies have demonstrated a direct relationship between the information gathered from retinal images and certain pathologies such as hypertension or diabetes. There are different works that present methodologies based on image processing algorithms to extract that information, but there is no globally accepted methodology to obtain the information automatically, which is the objective of this work. The proposed methodology has been evaluated by one expert user and compared with other existing free software with similar features.