Propuesta de un sistema de reconocimiento de placas salvadoreñas para la Universidad de El Salvador

Introduction: This article provides a proposal for a recognition system for Salvadoran license plates for the University of El Salvador. To arrive at this proposal, candidates based on free software were searched for in the most popular software repositories on the Internet. Objective: to propose a recognition system for salvadoran license plates for the University of El Salvador. Method: experimental, which made it possible to obtain data for processing and the results could be comparable. Candidates based on free software were searched for in the most popular software repositories on the Internet. The selected candidates were OpenALPR and the combination of YOLOv5 with PaddleOCR, and its installation was carried out in a test environment. A set of images of Salvadoran plates was then created to train and compare the models. The inferences of each candidate for each image of the set were obtained, as well as the correct answers, the time used and the certainty. Based on this information, the candidates
were compared with each other. Result: in each comparison item, the candidate with the best performance was the combination of YOLOv5 with PaddleOCR, becoming the proposed Salvadoran license plate recognition system for the University of El Salvador.