本文将小波算法、分水岭算法及基于区域的模糊 C 均值算法相结合,提出了一种基于规则的二次分割方法实现对脑组织磁共振图像的分割。首先,采用一种基于小波的滤波器去除图像中的噪声;然后采用分水岭算法实现对图像的初始分割。为克服分...本文将小波算法、分水岭算法及基于区域的模糊 C 均值算法相结合,提出了一种基于规则的二次分割方法实现对脑组织磁共振图像的分割。首先,采用一种基于小波的滤波器去除图像中的噪声;然后采用分水岭算法实现对图像的初始分割。为克服分水岭算法的过度分割问题,本文提出了基于区域的模糊 C 均值(RFCM)聚类算法实现对过度分割区域的合并。尽管分水岭算法存在过度分割现象,仍有一些区域分割得并不完全,尤其是在脑脊液与灰质,或灰质与白质的过渡区域。为此,本文提出一种局部区域连续性与全局信息相结合的基于规则的多阈值分割方法,对分水岭算法初始分割不完全的区域再次分割。通过对大量模拟数据和真实数据分割的实验证明了此方法的准确性和可靠性。展开更多
In recent years, due to its practical use in knowledge discovery and data mining, the research for rules reduction is becoming more important aspect of computer science. Based on rough set theory, a method of rules re...In recent years, due to its practical use in knowledge discovery and data mining, the research for rules reduction is becoming more important aspect of computer science. Based on rough set theory, a method of rules reduction for Dynamic Knowledge Systems is proposed in this paper. The experiments show the method is effective.展开更多
文摘本文将小波算法、分水岭算法及基于区域的模糊 C 均值算法相结合,提出了一种基于规则的二次分割方法实现对脑组织磁共振图像的分割。首先,采用一种基于小波的滤波器去除图像中的噪声;然后采用分水岭算法实现对图像的初始分割。为克服分水岭算法的过度分割问题,本文提出了基于区域的模糊 C 均值(RFCM)聚类算法实现对过度分割区域的合并。尽管分水岭算法存在过度分割现象,仍有一些区域分割得并不完全,尤其是在脑脊液与灰质,或灰质与白质的过渡区域。为此,本文提出一种局部区域连续性与全局信息相结合的基于规则的多阈值分割方法,对分水岭算法初始分割不完全的区域再次分割。通过对大量模拟数据和真实数据分割的实验证明了此方法的准确性和可靠性。
文摘In recent years, due to its practical use in knowledge discovery and data mining, the research for rules reduction is becoming more important aspect of computer science. Based on rough set theory, a method of rules reduction for Dynamic Knowledge Systems is proposed in this paper. The experiments show the method is effective.