<![CDATA[The advancement of artificial intelligence (AI) and digital image processing technologies has enabled the development of automated vehicle identification systems. This study aims to design a license plate classification system based on specific regional codes using the Optical Character Recognition (OCR) approach. The process involves several key stages, including image preprocessing (grayscale conversion, sharpening, noise reduction, and thresholding), character extraction via EasyOCR, and regional classification using Support Vector Machine (SVM) and Random Forest algorithms. The dataset consists of 1,920 vehicle plate images collected from two regions: BK (Medan) and BL (Aceh). Experimental results indicate that the SVM model achieved 86% accuracy, while the Random Forest model reached 84% accuracy. The system is deployed as a web-based application to facilitate automatic and efficient regional identification of vehicle plates. This research is expected to contribute to traffic monitoring systems and transportation security improvements]]>
Copyrights © 2025
