基于多结构多尺度形态学梯度的医学图像边缘检测

边缘检测在医学图像处理中占着至关重要的位置，检测的准确性将直接影响诊断和治疗。本文针对传统边缘检测算子对噪声敏感的不足，结合医学图像的特点，提出了一种形态学梯度运算的修正算法。首先由闭一开运算完成图像预处理以滤除噪声，再作闭运算平滑图像，最后对平滑的图像作多尺度的形态学梯度运算，得到噪声存在下的理想边缘，并将其用于医学图象的边缘检测。实验结果表明，该算法具有良好的边缘提取能力，抗噪性能良好，具有一定的实用性。

The edge- detection of medical image based on multi- scale morphological gradient

Edge detection plays an important role in medical imaging, the accuracy of detection will have a direct impact on diagnosis and treatment. In view of operators the shortages of sensitiveness to noise of conventional edge detection, considering the character of medical images, an amendment algorithm of the morphological gradient was proposed. First, pretreatment of the image are completed by close - open operation to eliminate noise; second, do close operation to smooth image,in the end, using the operation of morphological gradient for smoothing image, the ideal image edge trader the environment of existing noise is obtained,and it is applied to detect the edges of medical images. The experimental results show that this method can not only detect edge well,but also has the strong ability to suppress the noise in the image, and had some practicability.