自适应不同条件的车牌检测算法.

According to the problem of slow license plate detection and low detection accuracy under different conditions, this paper proposed an improved adaptive morphological closed and open operation to improve the license plate detection algorithm. The algorithm first used the local histogram to equalize the license plate image, and used the adaptive morphological closed operation to smooth all grayscale regions, and then introduced the local adaptive threshold processing to get the smooth image and the separated license plate. Finally, it adopted the morphological open operation to separate the connection parts between the external region and the number of the license plates. The experimental results show that the detection accuracy of the proposed method is higher than other algorithms. At the same time, the average detection time is less than other algorithms. The proposed method is suitable for real-time license plate detection under different conditions. [ABSTRACT FROM AUTHOR]