A novel scheme for binarization of vehicle images using hierarchical histogram equalization technique

TL;DR

This paper introduces a hierarchical histogram equalization-based binarization scheme for vehicle images, improving license plate recognition in challenging real-world scenarios with congested traffic.

Contribution

A novel hierarchical histogram equalization method that assigns membership values to pixels for improved binarization of vehicle images.

Findings

Effective binarization on vehicle and license plate datasets

Improved performance in congested road scenarios

Robustness against real-world image variations

Abstract

Automatic License Plate Recognition system is a challenging area of research now-a-days and binarization is an integral and most important part of it. In case of a real life scenario, most of existing methods fail to properly binarize the image of a vehicle in a congested road, captured through a CCD camera. In the current work we have applied histogram equalization technique over the complete image and also over different hierarchy of image partitioning. A novel scheme is formulated for giving the membership value to each pixel for each hierarchy of histogram equalization. Then the image is binarized depending on the net membership value of each pixel. The technique is exhaustively evaluated on the vehicle image dataset as well as the license plate dataset, giving satisfactory performances.