Graduate Project

Car license plate detection

In last couple of decades, the number of vehicles has increased drastically. With this increase, it is becoming difficult to keep track of each vehicle for purpose of law enforcement and traffic management. License Plate Recognition is used increasingly nowadays for automatic toll collection, maintaining traffic activities and law enforcement. Many techniques have been proposed for plate detection, each having its own advantages and disadvantages. The basic step in License Plate Detection is localization of number plate. The approach mentioned in this project is a histogram based approach. This approach has an advantage of being simple and thus faster. Initially, license plate localization is implemented using MATLAB and verified for its functionality. Once the functionality is verified, the algorithm is implemented on EVM320DM6437 Texas Instrument (TI) Digital Video Development Starter Kit (DVDSK). By implementing this algorithm on a kit, we eliminate need of computers and thus think of portable implementation of such application. In this approach, a digital camera is used to capture video and feed it to the kit. The kit processes each frame individually and provides the co-ordinates of location with maximum probability of having a number plate. Later, this information is used for recognizing actual number of the license plate. The plate detection algorithm is implemented in C, compiled and debugged using Code Composer Studio (CCS), an IDE provided by TI. Successful demonstrations were given by downloading the algorithm onto TI's EVM320DM6437 DVDSK.

Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.