License Plate Location Based on Haar-Like Cascade Classifiers and Edges

Abstract

License plate recognition is a core module for intelligent transportation systems, while license plate location is an important part of it. Haar-like cascade classifier is good for face detection, but its application to license plate localization largely depends on selection of positive and negative samples. In this paper we studied on how to choose good samples for Haar-like cascade classifiers and image post-processing methods to achieve good location results. It is hoped that the study could be useful to guide sample preparation for other object detection using Haar-like cascade classifiers.