中文说明：
通过引入折衷加权模糊因子和核度量，提出了一种改进的模糊C均值（FCM）图像分割算法。折衷加权模糊因子同时依赖于所有相邻像素的空间距离和它们的灰度差。利用该因子，新算法可以准确估计相邻像素的阻尼程度。为了进一步增强其对噪声和离群点的鲁棒性，我们在其目标函数中引入了核距离测度。该算法根据采集数据点的距离方差，采用快速带宽选择规则，自适应地确定核参数。此外，折衷加权模糊因子和核距离测度都是无参数的。在合成图像和真实图像上的实验结果表明，新算法是有效的，并且与这类噪声相对独立。
English Description：
An improved fuzzy C-means (FCM) image segmentation algorithm is proposed by introducing a compromise weighted fuzzy factor and kernel measure. The tradeoff weighted blur factor depends on both the spatial distance of all adjacent pixels and their gray difference. Using this factor, the new algorithm can accurately estimate the damping degree of adjacent pixels. In order to further enhance its robustness to noise and outliers, we introduce a kernel distance measure into its objective function. According to the distance variance of the collected data points, the algorithm adopts fast bandwidth selection rules to determine the core parameters adaptively. In addition, both the tradeoff weighted fuzzy factor and the kernel distance measure are nonparametric. Experimental results on synthetic images and real images show that the new algorithm is effective and relatively independent of this kind of noise.