A perspective correction method based on the bounding rectangle and least square fitting

Although Automatic License Plate Recognition (ALPR) systems have achieved high recognition speed and efficiency, perspective distortion may still affect the accuracy and reliability of ALPR due to the uncertainty of camera shooting angle. Some existing license plate correction methods are computational expensive and low robust. We proposed a perspective correction method based on the bounding rectangle and least square fitting. We extracted the bounding rectangle and the minimum bounding rectangle of each character. We use the least square method to fit a line for key points. Finally, the approach uses four vertices of license plate to get perspective transformation matrix and correct the distorted images. The results of our experiments show that our method is fast, accurate and robust.