Vehicle number plate detection and recognition using bounding box method

摘要

The use of vehicles in our life is increasing exponentially day by day and as increasing vehicles are violating the traffic rules, theft of vehicles, entering in restricted areas, high number of accidents lead to increase in the crime rates linearly. For any vehicle to be recognized, vehicle license plate detection will play a major significant role in this active world. For finding vehicles commonly used in field of security and safety system, LPDR plays a significant role and we need to recognize vehicles registration number at a certain distance. This paper has four major steps as follows: Preprocessing of captured image, Extracting license number plate region, Segmentation and Character Recognition of license plate. In pre-processing the desired vehicle image is taken through the digital camera, brightness of image is adjusted, noise removal using filters and image is converted to gray scale. Exactions of license plate region consist of finding the edges in the image where exact location of licenses plate is located and crop it into rectangular frame. Segmentation plays a vital role in vehicle licenses plate recognition; the legibility of character recognition completely relies on the segmentation done. The approach which we have used is simple but appropriate. First we segmented all characters in the image (LP) using Bounding box method. Finally, recognition of each character is done. The template matching method is used for recognition each character in the vehicle license plate.