License plate recognition based on temporal redundancy

Recognition of vehicle license plates is an important task in several real applications. Most approaches first detect a vehicle, locate the license plate and then recognize its characters. However, the focus relies on performing these tasks using only a single frame of each vehicle in the video. Therefore, such approaches might have their recognition rates reduced due to noise present in that particular frame. Instead of selecting a single frame to perform the recognition, we propose a novel real-time approach to automatically detect the vehicle and identify (locate/recognize) its license plate based on temporal redundancy information. To achieve further improvements, we also propose two post-processing techniques by querying a license plate database. The experimental results, performed in a dataset composed of 300 on-track vehicles acquired on an urban road, demonstrate that it is possible to improve the vehicle recognition rate in 15:3 percentage points using our proposal temporal redundancy approach. Additional 7:8 percentage points are achieved by querying registered license plates on a database by the vehicle appearance, leading to a final recognition rate of 89:6%. Furthermore, the technique is able to process 34 frames per second, which characterizes it as a real-time approach.