Philippine License Plate Localization Using Genetic Algorithm and Feature Extraction

Abstract

This study aims to focus on the license plate localization portion of an automated license plate recognition scheme. In order to achieve this, the study makes use of a genetic algorithm in order to perform a more systematic search over the input image; as well as Histogram of Oriented Gradients feature extraction technique in order to form the fitness function of the genetic algorithm. When the algorithm was tested, it was able to successfully localize the license plates within each of the multiple input images. In fact, even though the study was focused on 2014 series license plates, the program results also show that it was also able to roughly localize a license plate from another series as well.