A novel license plate localization method based on textural feature analysis

Automatic license plate localization in real-time environment is a complex task, due to the variety of sizes and colors as well as to the complexity of the background. In this paper we address this problem by proposing a novel localization scheme. The proposed approach is designed to work in a wide range of acquisition conditions, including unrestricted scene environments, camera-to-car distance, etc. A four-stage search process is proposed in this paper: pre-processing, approximate region searching, region classification and skew correction using Radon transform. Experiments have been preformed to prove the robustness and accuracy of the approach. The experiment results show that almost 96.1 % of input images are correctly localized on the average