This research presents a proposal for an artificial vision system, based on neural networks to identify defects in Yungay potato and Huevo de indio, caused by Premnotrypes Vorax. The objective of this research was to develop an artificial vision algorithm that allows the detection of potatoes with defects caused by the white worm. For the realization of the software, the Python programming language and the Tensorflow platform were used, through an experimental and quantitative trial and error methodology, the developed software allowed to identify and classify normal potatoes from potatoes with defects produced by the presence of Premnotrypes Vorax. . An efficiency level of 96.33% was achieved for the Yungay potato, while for the Huevo de Indio potato, the efficiency was 95.12%, observing that it is more effective in the Yungay potato. Concluding that the implementation of software with artificial vision is a good opportunity for improvement for farmers and agro-industries that produce potatoes because they would be more efficient when classifying potatoes.