Number plate Recognition and Character Segmentation using Eight-Neighbors and hybrid binarization techniques

Abstract

Number Plate Recognition (NPR) and Character Segmentation (CS) play a major role in one of the intelligent transportation system. This paper identifies a number plate identification system for Indian plates. This method consists of two main modules: NPR and CS. In NPR, histogram equalization is employed to solve the low contrast and dynamic-range problems and Eight-Neighbors technique is proposed to filter the unwanted areas in the image. In CS, the hybrid binarization technique is proposed to effectively segment the characters in the dirt NP. The system captures the images of the vehicles at various backgrounds and conditions using a digital camera. The results are highly appreciable.