摘要
定位汽车牌照在车牌识别应用中是很关键的一步。提出了一种基于数学形态学的新方法。以车牌宽度和高度、车牌字符高度及字间宽距等信息为依据来设计一种新的结构元,通过对汽车边缘图像进行形态学运算,能从图片中得到包含汽车牌照的候选区域,最后,基于汽车牌照纵宽比等固有特征,采用连通域体态分析,对包含车牌的多个候选区域进行去伪,得到真正车牌区域。通过对大量汽车图片实验,验证了该方法的有效性。
Locating the car license plate in a car image is an important step in car license plate recognition applications. This paper presents a new approach of extracting car license plate from car images based on morphology. Based on the information of combining width and height of car license plate, height of character and space between characters of the car license plate,some new structural elements for morphological operations are designed and used to detect the edge image of car license plate, which can produce several candidate areas. According to the intrinsic feature of height to width ratio for a car license plate, connected component analysis is performed and the car license plate area is isolated. The results of experiments with a reasonably large set of car images are very encouraging.
出处
《青岛科技大学学报（自然科学版）》
CAS
2007年第1期69-72,共4页
Journal of Qingdao University of Science and Technology:Natural Science Edition
关键词
车牌提取
蒲瑞维特算子
数学形态学
结构元
car license plate extraction
prewitt operator
math morphology
structuring element
