| 摘要: |
| 针对目前基于 FCM 的改进算法不能很好解决图像分割的精度和速率问题,提出了一种改进的FCM 算法来对图像进行有效率的分割。 在算法中加入抑制因子增加算法的聚类速率;在原有 KFCM 算法的目标函数中加入加权模糊因子增加像素的空间信息,从而解决算法分割精度的问题。 通过对比实验图可看出:改进的算法对原图像分割的效果更佳,而且对噪声的抑制效果较为明显,再通过引入评价指标的实验数据可以直观看出改进的算法不仅对原灰度图像而且对噪声图像都具有较好的分割性能,对噪声和孤立点都具有较好的鲁棒性和抑制性,表明了改进的算法能够大大提高人们的工作效率,同时为后期再次改进提出一
种思路和方向。 |
| 关键词: 模糊聚类 图像分割 FCM IFCM KFCM 空间信息 |
| DOI： |
| 分类号: |
| 基金项目: |
|
| Research and Application of Image Segmentation Based onImproved FCM Algorithm |
|
ZHU Kai-Jun
|
|
School of Electrical and Information Engineering, Anhui University of Science and Technology,
Anhui Huainan 232001, China
|
| Abstract: |
| In view of the problem that the improved algorithms based on FCM can not solve the problem of accuracy and speed of image segmentation, an improved algorithm based on FCM is proposed to efficiently segment images. An inhibitor is added to the algorithm to increase the clustering rate of the algorithm. Weighted fuzzy
factors are added to the target function of the original KFCM algorithm to increase the spatial information of pixels to solve the problem of segmentation accuracy of the algorithm. It can be seen from the graphs of the comparison experiments that the improved algorithm has a better effect on the original image segmentation, and the effect of noise suppression is more obvious. Through the experimental data of the introduced evaluation index, it can be seen intuitively that the improved algorithm not only has better segmentation performance for the original gray image and noise image, but also has better robustness and inhibition for noise and isolated points. It shows that the improved algorithm can greatly improve people’s work efficiency, and proposes a way of thinking and direction for people to
improve again in the future. |
| Key words: fuzzy clustering image segmentation FCM IFCM KFCM spatial information |
