Registration Plate Recognition Using Dynamic Image Processing and Genetic Algorithm

Abstract

Registration plate recognition plays a vital role in numerous applications in today’s world. We also introduce a new approach using genetic algorithm to figure out the registration plate location. Fluctuating illumination conditions are taken care-of by adaptive threshold method. Connected element tagging is used to identify the objects in blindfolded regions. A matrix of invariant scale geometry is used for better system adaptability when applied to different plates. The convergence of genetic algorithm is greatly improved by the introduction of a newly created mutation and crossover operators. We also modify genetic algorithm to overcome the drawbacks of connected element method by importing partial matching of the characters. Finally, we take a look at the real-time challenges and remedies to it.