Optimized Two-Stage Ensemble Model for License Plate Recognition

Pattern recognition models play an important role in many real-world applications such as text detection and object recognition. Numerous methodologies including Computational Intelligence (CI) models have been developed in the literature to tackle image-based pattern recognition problems. Focused on CI models, this research presents efficient Particle Swarm Optimization (PSO)-based models and their application to license plate recognition. Firstly, a new Reinforcement Learning-based Memetic Particle Swarm Optimization (RLMPSO) model is introduced. Then, RLMPSO is integrated with the Fuzzy Support Vector Machine (FSVM) to formulate an efficient two-stage RLMPSO-FSVM model. Specifically, two-stage RLMPSO-FSVM comprises an ensemble of linear FSVM classifiers that are constructed using RLMPSO to perform parameter tuning, feature selection, as well as training sample selection. Finally, the proposed two-stage RLMPSO-FSVM model is applied to a real-world Malaysian vehicle license plate recognition (VLPR) task.

Autorentext

Dr. Hussein Samma has a B.S.c in computer engineering (Yarmouk University - Jordan), M.Sc. in computer engineering (Jordan University of Science and Technology, Jordan), and Ph.D. in computational intelligence (Universiti Sains Malaysia, Malaysia). His research interest in pattern recognition, computer vision, soft computing, and soft bio-metrics.