图像校正技术的研究及应用

基于单应性矩阵方法研究了图像校正技术,该方法的关键问题在于边缘检测及寻找边缘的交点。针对车牌图像的校正,提出了一种自动化的边缘提取方法。该方法通过对霍夫变换得到的直线进行合并、分类、排序等方法来自动获取图像边缘并计算相应的交点。对校正后的图像因为长宽比例不同而产生的问题,作了分析和相应处理。该方法保留了单应性矩阵恢复算法的方便性,同时速度更快,取得的效果也比较好。

Research and Application of Image Calibration

The image calibration based on homography matrix method is studied.The key problems of this method are edges detection and looking for their intersections.A new automatic edge detection method is put forward to the calibration of license plates.The method obtains the edges of pictures and their intersections through merging,sorting and ranging based on Hough transformation automatically.For problems result from different proportions of length and width,the analysis and relative processing are given.Simulation result shows that this method has good performance as well as preserving the convenience of homography matrix calibration.