一种新的汽车牌照识别的图像增强算法  

A new image enhancement algorithm for car license plate recognition

作　　者：宋焕生[1] 赵祥模[1] 王养利[2] 

机构地区：[1]长安大学信息工程学院,陕西西安710064 [2]西安电子科技大学计算机学院,陕西西安710071

出　　处：《长安大学学报（自然科学版）》2006年第4期75-78,91,共5页Journal of Chang’an University(Natural Science Edition)

基　　金：国家自然科学基金项目(60272050);教育部新世纪优秀人才支持计划项目(NCET-05-0849)

摘　　要：汽车牌照区域分割是牌照识别的关键步骤,增强图像中的牌照区域,抑制背景区域,可以有效降低牌照区域分割的难度。将图像分解为一组二值图像的组合,然后在二值图像上计算各连通分量及其特征参数,利用牌照区域和背景区域对应的连通分量的特征差别,可以有效抑制背景而保留牌照。处理后的二值图像可重构出牌照区域被增强的图像。还采用等高线标记代替连通分量标记,以减少计算量,使得算法具有实用性。试验表明,这种算法有效地突出了牌照区域而抑制了背景,提高了牌照定位分割的效果,可以很好地用于实际的汽车牌照识别系统中。Segmentation of license plate region is a key procedure in a car license plate recognition system, enhancing the plate region of the captured image and suppressing the background area can effectively reduce the difficulty of the plate segmentation task. The image used for license recognition is decomposed into a group of binary versions, and then connected regions in the binary images are labelled and their feature parameters are calculated. As the connected regions in the plate area and those in the background are very different in the calculated feature parameters, so the connected regions which likely belong to the plate area can be preserved and the others can be erased. A new image with plate region enhanced can be reconstructed from the processed binary images. In order to reduce the computation load and make the algorithm realizable, contour lines instead of connected component labelling is utilized to describe the connected regions. The experimental results show that the proposed algorithm can effectively enhance the plate area and suppress the background area, improve the plate segmentation performance. The new algorithm can be well applied in the real car license plate recognition systems. 4 figs, 8 refs.

关 键 词：交通工程 汽车牌照识别 图像处理 图像增强 连通分量 等高线 

分 类 号：U491.116[交通运输工程—交通运输规划与管理] TN919.8[交通运输工程—道路与铁道工程]