The objective was to implement an artificial neural network to improve the recognition of geometric figures that later allow making estimates about shapes in a real context to create virtual planes. A Matlab program was developed to create the neural network and two knowledge bases containing fifteen different geometric figures that were developed for the training stage and for the recognition stage. The results of the training phase were carried out in three processes, obtaining a percentage of 11.35%, 3.55%, and 2% error margin respectively, later came the recognition stage with three processes, obtaining 40%, 100%, and 100% figures recognized respectively. It is concluded that the implemented neural network performed the recognition of fifteen geometric figures correctly (100%), requiring three training processes and three recognition processes to verify their learning.
Keywords: Image recognition, Machine learning, artificial neural networks, artificial intelligence.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.