中文摘要：

车牌定位是车牌识别系统的关键技术之一。为了快速准确地定位车牌，文章提出一种改进的金字塔变换和数学形态学的车牌定位算法。首先通过金字塔变换进行预处理，增强图像的细节信息，减弱环境和光照等条件变化对车牌定位的影响；然后利用图像二值化和数学形态学技术形成包含车牌的若干候选区，在此基础上设计了一种“先周边后中心”的车牌提取算法；最终准确定位出车牌位置，提取出车牌图像。通过对不同地点、不同自然条件下采集的图像进行测试，得出定位准确率为99．2％、平均定位时间为0．309S，证明了该车牌定位算法准确可行，具有良好的性能。

英文摘要：

License plate location is one of the key technologies of license plate recognition system. In order to locate the vehicle license plate rapidly and accurately, a new license plate location algorithm based on improved pyramid transform and mathematical morphology technology is put forward. First, the algorithm of pyramid transform is applied to vehicle image to enhance image detail and reduce the impact of environment and lighting conditions change on the vehicle license plate location. Secondly, the candidate regions of license plate are identified by using image binarization and mathematical morphology technique. On this basis, a new license plate extraction method is designed which first eliminates surrounding interference areas and then center interference areas. By the method, the license plate location is accurately located and the license plate image is extracted eventually. Tests are done on images collected from different places and different natural conditions. The test results show that the success rate of license plate location is 99. 2% and the average positioning time is 0. 309 s, thus proving that the proposed method is accurate and feasible for license plate location.