Robust vehicle license plate localization using To-MACH filter

Detecting the region of a license plate is the key component of the vehicle license plate recognition system. The spatial frequency characteristic in the license plate region usually varies more than in the background. In this paper, we propose a new approach for vehicle license plate localization using an optimal trade-off maximum average correlation height (TO-MACH) filter in the frequency domain. The proposed algorithm consists of two main stages. Initially, we get a single image template as the TO-MACH filter by training several examples of the license plate image. Finally, the filter is correlated with the test image to locate the license plate; the accurate license plate region can be get by projection method. Experimental results show that our method can accurately and robustly locate vehicle license plate when source image are captured from complex environments, such as poor illumination, varied distances from the vehicle and varied weather etc.