Philippine License Plate Detection and Classification using Faster R-CNN and Feature Pyramid Network

Abstract

The advancement of image and video processing using Artificial Intelligence (AI) have brought more significance to the role of Automatic License Plate Recognition (ALPR) systems in law enforcement and intelligent transport systems (ITS). However, the adaptation of such a system in the Philippines has been a challenge due to the different variations of Philippine license plates. In this paper, a neural network-based model for the detection and classification of different Philippine license plate formats is proposed. The proposed method classifies license plates into four categories — 1981, 2003, 2014, and other series.