车牌识别中的图像提取及分割算法

Image Extraction and Segment Arithmetic of License Plates Recognition

提出一种梯度增强法对图像边缘进行增强,该方法主要通过对图像本身信息进行简单梯度变换以突出图像边缘,并辅以数学形态学中的膨胀法实现牌照的快速定位.在字符分割部分,给出了最小面积旋转法以确定牌照的最佳旋转角,并采用垂直投影法分割牌照中的字符.

A grad intensity method is put forward to process edges＇ intensity of an image, this measure mostly uses simple grad transform to potentate the image edges, at the same time, a dilation method of mathematical morphology is applied to achieve rapid orientation of the license plates. In the process of characters segmentation, we first proposed least area circumrotation means in order to ascertain the best rotation angle of the license plate, then we adopted the way of perpendicularity projection to segment the characters of the license plate.