Implementasi Automatic License Plate Recognition untuk mengurangi pelanggaran lalu lintas berbasis Artificial Intelligence

Abstrak

Abstract - Indonesia is a country with an increasing number of vehicles each year. However, with the growing traffic density in urban areas, traffic violations such as disregarding traffic signs and exceeding speed limits often occur. This research aims to implement the Automatic License Plate Recognition (ALPR) system using the K-Nearest Neighbors (KNN) algorithm to predict and recognize vehicle license plates in plate images. The research also aims to evaluate the accuracy level of the implemented ALPR system. The method used in this research is KNN, which is one of the classification methods in machine learning. The training data used consists of a collection of preprocessed vehicle license plate images. After the training process, the system can recognize and predict vehicle license plates in new plate images. The research results show that the implemented ALPR system using the KNN algorithm can achieve an accuracy level of 93% in recognizing vehicle license plates. This success demonstrates that KNN is an effective algorithm for license plate recognition in plate images. This research has important implications for the development of ALPR systems that can be used for various purposes such as traffic surveillance, security, and law enforcement.