An algorithm for automatic license plate detection from video using corner features

As the importance of public transit system increases an Automatic License Plate Recognition (ALPR) has turned out to be an important research subject. It is getting hard to preserve track of each vehicle for purposes of law enforcement and traffic management. ALPR equipped with many intelligent surveillance systems like, road traffic management, security management, automatic toll collection system, etc. The basic steps in ALPR were accurate localization of number plate, which bears on the overall system accuracy. A license plate detection method was produced to find number plates from a continuous video stream showing the movement of all the vehicles in various conditions such as, non-uniform illumination, vehicle speed, background and foreground color, different weather condition, occlusion within image, etc. In this composition, the detection of a license plate from an image, corner features based on Harris algorithm is proposed and been simulated The advantages of the algorithm are high speed, accuracy and less complexity. The License plate(s) was extracted successfully from an input video file. The comparison is made between the wavelet transform based algorithm and Harris corner algorithm on the basis of accuracy of multiple license plate detection.