A Study of License Plate Location based on Mathematical Morphology and Wavelet Transform

F. Yang and Z. Ma (PRC)

Keywords

License plate location, Mathematical morphology, Wavelet transform

Abstract

In this paper, a method of locating license plate based on mathematical morphology and wavelet transform is presented. At first, we calculate the vertical gradient of original image. Then we perform mathematical morphology on the vertical gradient and obtain the horizontal candidates from the horizontal projection of gradient variance. Wavelet transformation is used in the following with the purpose of extracting Multi-resolution feature from candidates. Finally, accurate vertical position of license plate is detected and license plate is extracted from the original image. Experiments have been conducted on 360 images taken from various scenes and different conditions including diverse angles, different lightening conditions and the dynamic conditions. The algorithm can quickly and correctly detect the region of license plate and the license plate detecting rate of success is 98. 61%.

Important Links:



Go Back


IASTED
Rotating Call For Paper Image