結(jié)合非局部信息的模糊聚類腦MR圖像分割
發(fā)布時(shí)間:2018-08-17 19:09
【摘要】:為降低噪聲以及偏移場(chǎng)的影響,提出一種基于非局部空間信息的FCM模型。引入非局部信息,克服傳統(tǒng)的空間信息僅依賴鄰域灰度信息,導(dǎo)致精度不高的缺點(diǎn),使其在降低噪聲影響的同時(shí)保持細(xì)長拓?fù)浣Y(jié)構(gòu)區(qū)域信息;利用多元高斯分布模型對(duì)圖像灰度分布進(jìn)行擬合,構(gòu)造距離函數(shù),降低傳統(tǒng)歐式距離導(dǎo)致魯棒性不足的影響;利用基函數(shù)的線性組合對(duì)偏移場(chǎng)進(jìn)行擬合,將偏移場(chǎng)參數(shù)化并耦合到FCM框架下,降低灰度不均勻?qū)Ψ指畹挠绊。?shí)驗(yàn)結(jié)果表明,該模型可以得到更精確的分割結(jié)果。
[Abstract]:In order to reduce the influence of noise and offset field, a FCM model based on nonlocal spatial information is proposed. The nonlocal information is introduced to overcome the disadvantage that the traditional spatial information only depends on the gray level information of the neighborhood, which leads to the low precision, which can reduce the influence of noise and keep the information of the slender topological structure region at the same time. The multivariate Gao Si distribution model is used to fit the gray distribution of the image, and the distance function is constructed to reduce the influence of the traditional Euclidean distance on the robustness, and the linear combination of the basis function is used to fit the offset field. The offset field is parameterized and coupled to the FCM framework to reduce the influence of gray inhomogeneity on segmentation. Experimental results show that the model can obtain more accurate segmentation results.
【作者單位】: 南京信息工程大學(xué)數(shù)學(xué)與統(tǒng)計(jì)學(xué)院;
【基金】:江蘇省自然科學(xué)基金項(xiàng)目(BY2014007-04)
【分類號(hào)】:R445.2;TP391.41
本文編號(hào):2188610
[Abstract]:In order to reduce the influence of noise and offset field, a FCM model based on nonlocal spatial information is proposed. The nonlocal information is introduced to overcome the disadvantage that the traditional spatial information only depends on the gray level information of the neighborhood, which leads to the low precision, which can reduce the influence of noise and keep the information of the slender topological structure region at the same time. The multivariate Gao Si distribution model is used to fit the gray distribution of the image, and the distance function is constructed to reduce the influence of the traditional Euclidean distance on the robustness, and the linear combination of the basis function is used to fit the offset field. The offset field is parameterized and coupled to the FCM framework to reduce the influence of gray inhomogeneity on segmentation. Experimental results show that the model can obtain more accurate segmentation results.
【作者單位】: 南京信息工程大學(xué)數(shù)學(xué)與統(tǒng)計(jì)學(xué)院;
【基金】:江蘇省自然科學(xué)基金項(xiàng)目(BY2014007-04)
【分類號(hào)】:R445.2;TP391.41
【相似文獻(xiàn)】
相關(guān)碩士學(xué)位論文 前10條
1 周連波;基于局部信息的復(fù)雜網(wǎng)絡(luò)社團(tuán)挖掘算法研究[D];燕山大學(xué);2015年
2 于健;帶有隨機(jī)擾動(dòng)的風(fēng)場(chǎng)優(yōu)化調(diào)度策略的研究[D];北京交通大學(xué);2016年
3 牛會(huì)蘭;局部信息方法在功能腦網(wǎng)絡(luò)建模中的應(yīng)用研究[D];太原理工大學(xué);2016年
4 賈桂敏;基于物體局部信息的跟蹤算法研究[D];天津大學(xué);2008年
5 龍麗君;網(wǎng)絡(luò)內(nèi)容監(jiān)管系統(tǒng)中基于局部信息的語義傾向性識(shí)別算法[D];南京理工大學(xué);2004年
6 王聰;基于局部信息交流的命名游戲問題研究與應(yīng)用[D];大連理工大學(xué);2013年
7 謝德燕;局部信息保持投影及應(yīng)用[D];西安電子科技大學(xué);2010年
8 楊雨澤;基于整體和局部信息的多經(jīng)驗(yàn)核學(xué)習(xí)及其應(yīng)用研究[D];華東理工大學(xué);2014年
9 夏磊;一種基于局部信息的社會(huì)網(wǎng)絡(luò)聚類算法[D];哈爾濱工程大學(xué);2012年
10 陳書楊;局部信息缺失情況下人臉識(shí)別研究[D];遼寧大學(xué);2014年
,本文編號(hào):2188610
本文鏈接:http://sikaile.net/yixuelunwen/fangshe/2188610.html
最近更新
教材專著