基于颜色和纹理特征相结合的车牌定位方法

The Method of License Plate Location Based on Color and Texture Analysis

车牌定位是车牌自动识别系统中的关键技术.目前多数的车牌定位方法考虑车牌的颜色以及纹理特征,但针对复杂背景下的车牌定位问题,其适应性不强.针对现实生活中复杂背景下的车牌定位,提出综合使用纹理信息及颜色信息等多种特征的分层次车牌快速定位方法.首先在图像的二值垂直边缘图中,利用车牌区域的边缘信息及车牌的纹理特征进行车牌候选区域的确定,在降低算法复杂度的同时提高了定位精确性,然后结合先验知识,运用四元数主成分分析及K-means聚类方法,提取候选区域图像特征并分类,最终得到精确车牌定位.试验证明该方法正确率高、鲁棒性强,对于背景复杂的车牌定位具有很强的抗干扰性能,在复杂的环境和不同光照条件下实现车牌的精确定位.

License plate location is the key technology of license plate recognition. At present license plate color and texture feature were considered in the most license plate location methods, however, these methods had weak adaptability in different environment. So,a new algorithm for license plate location in complex backgrounds is proposed. This algorithm makes full use of the color, texture and geometric characteristics. Firstly the edge information and the texture features of license plate region are used to identify the candidate plates. The complexity of the algorithm is reduced and the accuracy of positioning is also improved. Then combined with prior knowledge,quaternion principal component analysis and K- means clustering method are used to extract features from the candidate area and to classify image by the features, the precise plate is got eventually. This method is proved effective with high speed and accuracy. In particular, it has strong robust performance for complex backgrounds images in complex environments and different lighting conditions.