Abstract:

An adaptive Fuzzy C-Means(FCM) method for image segmentation based on fuzziness rate is proposed. It automatically determines the proper number of fuzzy clustering by utilizing the gradient detection method of wave trough and peak. Accurate original cluster centers are acquired by utilizing fuzzy threshold method. A novel objective function is established which contains feature information and spatial information. Experimental results show that the method has fast segmentation speed and high segmentation accuracy, and has stronger robustness.

Key words: fuzzy clustering, image segmentation, fuzzy threshold, neighbor information, robustness

摘要：

提出一种基于模糊率的模糊C均值自适应图像分割方法。该方法根据波谷波峰梯度检测法自动确定模糊聚类数目，利用模糊阈值法快速确定较为准确的初始聚类中心，建立包含特征信息和空间信息的新目标函数，实现图像的自动分割。实验结果表明，该方法的分割速度快、精度较高，具有较强的鲁棒性。

关键词: 模糊聚类, 图像分割, 模糊阈值, 邻域信息, 鲁棒性

CLC Number: 

• TP391.41