中文摘要：

针对Mean Shift算法在图像平滑过程中由于过平滑现象而导致平滑区域易出现边缘模糊问题,提出一种基于二次核函数的Mean Shift图像平滑算法,该算法利用核函数对采样点加权,通过Mean Shift向量迭代至灰度概率密度最大处,并将此灰度值赋予当前像素点,依次遍历每个像素点,不断聚类对图像进行平滑.此外,在四幅标准图像上对算法进行了仿真实验.并在视觉效果和量化评价等方面,与基于另外四种核函数的Mean Shift图像平滑算法进行了实验比较.实验结果表明,本文算法在最大限度地平滑掉图像多余细节和噪声的同时,能够保证图像被平滑区域的边缘不被模糊.

英文摘要：

Concerning the problem that there are some drawbacks such as edge blur existed in some image smoothing algorithms based on mean shift, a quadratic kernel-based Mean Shift image smoothing algorithm was proposed and tested on four standard images in this paper. The algorithm firstly uses the kernel function to weight the sample point; then, the gray value of each pixel is iterated to the maximum gray probability density by using the Mean Shift vector; next,the iterated gray value is assigned to the current pixel; final- ly, the image is smoothed by traversing and clustering the current pixel. In addition, the proposed algorithm was compared with the Mean Shift smoothing algorithms based on other four kernels in terms of visual and quantitative evaluation. The results indicate that the proposed algorithm can effectively remove the details and noises in image, and protect the edges of image at the same time.