无监督模糊C均值聚类自然图像分割算法

提出一种基于无监督模糊C均值聚类的彩色自然图像分割算法。使用置信区间交集准则自适应得到Gabor滤波器中各个像素点对应的尺度，并以该自适应尺度为依据，计算相应的自适应方向、频率以及相位；使用该自适应Gabor滤波方法分别对各通道进行纹理分析得到相应的纹理图像。提出一种快速的基于多项式分割的方法对各个纹理图像进行分析，确定聚类数目，并使用无监督模糊C均值聚类算法得到最终的分割结果。实验结果表明，该算法能够很好地克服图像纹理对于分割结果的影响，有效区分目标与背景，分割结果具有较高的分割精度，是一种有效的自然彩色图像分割方法。

Natural image segmentation algorithm with unsupervised FCM

In this work, we propose a natural image segmentation method based on unsupervised fuzzy C-means (USFCM) clustering algorithm. The intersection of confidence intervals rules is utilized to adaptively compute the scale of Gabor filter for each pixel. Then image features are measured by Gabor filter with adaptively computed scale, orientation, frequency and phase. Meanwhile, a fast polynomial segmentation method is proposed to determine the number of clusters. Then the algorithm USFCM is utilized to get the final segmentation. The experimental results show that the proposed method can overcome the impact of texture and distinguish the target from background. The performances have demonstrated the effectiveness, accuracy and superiority of the proposed method.