Plate Recognition Using Fuzzy Noise Removal and Opposition-based Micro-Differential Evolution

Automatic plate recognition of vehicles is of greatimportance in route management systems. Especially that suchsystems require real-time algorithms to perform the platerecognition task as soon as possible. In this paper, a new platerecognition system based on a fuzzy noise removal technique andthe opposition-based micro-differential evolution (OMDE)algorithms is presented. Since population-based algorithms aremostly working based on a large population size, which results ina high computational cost, the micro-population-based algorithmrequire a very small population size and as a result, lesscomputational cost. However, due to lack of diversity in suchalgorithms, the idea of opposition-based learning is utilized toenhance the diversity in the search procedure. By employing thetemplate matching method, the digits and alphabets are easilyextractable from plate image. Performance evaluation of theproposed system shows that this system is capable of identifyingthe vehicle’s plate with high quality in route management systems

کلیدواژه ها:

micro-differential evolution ، plate recognition ، opposition learning ، template matching