脑外科CT图像的综合边缘提取算法

An integrated algorithm of edge detection of brain surgery CT image

为了实现大脑的三维重建,准确提取二维图像中的边缘成了首要解决的问题。常用的几种经典边缘检测算子对噪声比较敏感,容易造成虚假或不连续的边缘。针对此问题,提出基于Canny算子并结合图像增强和数学形态学的综合边缘提取算法。该算法首先对原始图像进行增强,以便于计算机的分析;然后利用Canny算子对CT图片进行边缘提取,该算子具有非极大值抑制和双阈值法连接边缘的优点,但容易将非边缘点检测为边缘,而且存在边缘不连续的问题;最后利用数学形态学中的膨胀方法对提取的边缘进行处理。实验结果表明,该算法提取的边缘光滑连续,为后面大脑的三维重建打下了坚实的基础。

In order to achieve the three-dimensional reconstruction of the brain, it is the first issue of extracting the edge of two-dimensional image accurately . Several common classic edge detection operators were sensitive to noise, and they were easy to cause a false or discontinuous edge. For this problem, this paper presented a integrated edge detection algorithm,which was based on Canny operator and the combination of image enhancement and mathematical morphology. First, we did a image enhancement to the original images, which was convenient for the computer analysis; then the edge of brain image was extracted by the Canny operator, the operator has two advantages of non-maxima suppression and double-threshold method to connect the edge, but the non-edge point was easily detected the edge, and there was still some edges discontinuity; lastly, the extracted edge was disposed by the expansion of the mathematical morphology method. Experimental result shows that the extracted edge is smooth and continuous, it lay a solid foundation for the three-dimensional reconstruction of the brain in future.