With the study of existing dimming methods and the consideration of the current research situation about AEC algorithm, an original feedback auto dimming algorithm based on image strategy which use the information of histogram of license plate has been proposed in this paper. The algorithm which has been presented uses distribution of histogram of license plate to judge the exposure information, and then takes advantage of the judgement information by adjusting brightness base under brightness mode to achieve automatic exposure control at the circumstance of complex lighting conditions, which overcomes the drawbacks of existing dimming methods. Meanwhile, the procedures of how above dimming algorithm works has been introduced in detail and then the algorithm has been effectively tested in practice. Finally, the algorithm is a field test conducted field tests based on the existing dimming method of "Smart Zhitong Eye". The experimental results show that the proposed algorithm can effectively improve the recognition rate compared with the traditional dimming algorithm of license plate recognition, and can be directly applied in the front-end embedded video acquisition and recognition of license plate capture equipment.