Desarrollo de un sistema para la identificación automática de marcas y modelos de autos usando algoritmos de aprendizaje de máquina y visión por computador.

Abstract

This academic article details the creation of a system that uses Machine Learning and Computer Vision algorithms for the detection of 10 models and brands of cars with more demand in our country, encouraging the creation of solutions that can be complemented with software developed mainly for the detection of license plates. The main objectives lead to phases that will be part of the structuring of the methodology. Obtaining as results a 14% error of classification of the 10 models and brands of vehicles by means of images or photographs. It was also possible to evaluate the algorithms by means of metrics that verified their correct operation and coherence in their classified results.