本文選題：圖像分割 + 水平集　； 參考：《西南交通大學(xué)》2016年博士論文

【摘要】：隨著電子計(jì)算機(jī)技術(shù)的發(fā)展,數(shù)字圖像處理作為一門新興的學(xué)科已經(jīng)成為信息社會(huì)中必不可少的工具。圖像分割作為圖像處理和計(jì)算機(jī)視覺、目標(biāo)跟蹤、以及醫(yī)療成像的基本課題,其主要目的是把圖像分割成一系列具有均勻特性(灰度、顏色、紋理等)的子區(qū)域,進(jìn)而將感興趣的目標(biāo)從背景中提取出來。在過去的幾十年中,研究人員已經(jīng)做出很大的努力來解決圖像的分割問題,并提出了很多分割算法。然而,由于存在噪聲、復(fù)雜背景、低信噪比和灰度不均勻性等問題,圖像分割仍然是一項(xiàng)具有挑戰(zhàn)性的任務(wù)。為了改善圖像分割算法的性能,國內(nèi)外學(xué)者至今仍在探索和開發(fā)新的圖像分割算法和分割理論,以得到通用性更好、精度更高的分割結(jié)果,這也是本論文選題的意義所在。模糊C均值(Fuzzy C-Means, FCM)算法以最小平方誤差和來衡量樣本點(diǎn)與聚類中心之間的相似性,利用迭代法優(yōu)化目標(biāo)函數(shù),從而實(shí)現(xiàn)圖像數(shù)據(jù)的最優(yōu)聚類。由于成功地將模糊關(guān)系引入到聚類方法中,使得FCM算法保留了更多的原始圖像信息�；谄⒎址匠痰幕顒�(dòng)輪廓模型憑借其自由的拓?fù)浜挽`活的結(jié)構(gòu),得到了眾多研究者們的青睞。該方法既利用了低層的圖像信息,又融入了高層的理解機(jī)制,因而能獲得精確的分割結(jié)果,具有較強(qiáng)的魯棒性和實(shí)用性。本學(xué)位論文主要探討圖像分割領(lǐng)域中的模糊聚類和活動(dòng)輪廓模型這兩類分割方法,在原有算法的基礎(chǔ)上進(jìn)行改進(jìn),取得了如下研究成果：(1)提出了一種基于局部變異系數(shù)的模糊C均值圖像分割算法。首先,利用局部窗口內(nèi)所有像素點(diǎn)灰度的中值來代替中心點(diǎn)像素的灰度值,對快速廣義模糊C均值(Fast Generalized Fuzzy C-Means, FGFCM)算法中的局部灰度相關(guān)性矩陣Sg_ij進(jìn)行修正,提高了算法抑制噪聲的能力；然后,引入局部變異系數(shù)來重新構(gòu)造像素間的局部相似性度量,使其能更好地控制鄰域內(nèi)各點(diǎn)對中心像素的權(quán)重；最后,利用快速分割的思想使分割過程僅依賴于圖像的灰度級,從而可以進(jìn)一步提高算法的運(yùn)行效率。與同類方法相比,該算法在一定程度上提升了圖像的分割效果,且對噪聲有很強(qiáng)的魯棒性。(2)提出了一種局部交叉熵度量模糊C均值的水平集圖像分割算法以及它的簡化模型。首先,鑒于交叉熵準(zhǔn)則在處理噪聲方面有較大的優(yōu)勢,將其取代平方誤差和準(zhǔn)則來重新構(gòu)造FCM_S (Fuzzy C-Means with Spatial Constraints)算法的目標(biāo)函數(shù),這樣處理可以自適應(yīng)地增加或減小樣本點(diǎn)屬于某個(gè)聚類的程度；其次,將改進(jìn)后的聚類算法融入到變分水平集框架中,使得模型可準(zhǔn)確地對像素點(diǎn)進(jìn)行歸類；最后,采用加權(quán)迭代法和梯度下降流法來求解本章模型。實(shí)驗(yàn)結(jié)果顯示,相對于傳統(tǒng)的水平集算法,該方法能成功地處理弱邊緣和灰度不均勻目標(biāo),且具有一定的抗噪性。(3)提出了一種基于局部符號差和局部高斯分布擬合能量的活動(dòng)輪廓模型。該模型以引入圖像局部熵的局部符號差(Local Signed Difference, LSD)能量項(xiàng)和局部高斯分布擬合(Local Gaussian Distribution Fitting, LGDF)能量項(xiàng)的線性組合來構(gòu)造水平集函數(shù)的演化力,并運(yùn)用梯度下降流法來求解該能量泛函,從而驅(qū)使曲線向目標(biāo)邊緣運(yùn)動(dòng)。與傳統(tǒng)的活動(dòng)輪廓模型相比,新方法能正確地提取灰度不均勻圖像中的目標(biāo),且對初始輪廓曲線的大小、位置和形狀更不敏感。(4)提出了一種基于區(qū)域生長初始化的水平集海馬圖像分割算法。首先,通過自適應(yīng)區(qū)域生長算法來獲取海馬體的大致區(qū)域；其次,對生長出的結(jié)果進(jìn)行形態(tài)學(xué)操作,以消除內(nèi)部斑點(diǎn),并進(jìn)一步利用輪廓跟蹤算子得到有序的海馬輪廓線；最后,將此輪廓曲線作為先驗(yàn)信息,運(yùn)用改進(jìn)的水平集方法驅(qū)動(dòng)輪廓曲線向目標(biāo)靠近并在海馬邊界處停止。實(shí)驗(yàn)結(jié)果顯示,該算法分割出的海馬結(jié)果與專家手動(dòng)分割得到的結(jié)果非常相近,具有較好的準(zhǔn)確性和分割效率。
[Abstract]:With the development of computer technology, digital image processing, as a new subject, has become an indispensable tool in the information society. Image segmentation is the basic subject of image processing and computer vision, target tracking, and medical imaging. The main purpose of image segmentation is to divide the image into a series of uniform characteristics (gray scale, In the past few decades, researchers have made great efforts to solve the problem of image segmentation and put forward a lot of segmentation algorithms. However, there are some problems, such as noise, complex background, low signal to noise ratio and gray scale inhomogeneity, and so on. Cutting is still a challenging task. In order to improve the performance of the image segmentation algorithm, scholars at home and abroad are still exploring and developing new image segmentation algorithms and segmentation theories to get better universal and more accurate segmentation results. This is also the significance of this topic. Fuzzy C mean (Fuzzy C-Means, FCM) algorithm Using the minimum square error and the similarity between the sample point and the cluster center, the optimal clustering of the image data is realized by using the iterative method to optimize the target function. The FCM algorithm preserves more original image information because of the success of introducing the fuzzy relation into the clustering method. By virtue of its free topology and flexible structure, it has been favored by many researchers. This method not only uses the low layer image information, but also integrates the high-level understanding mechanism, so it can obtain accurate segmentation results and have strong robustness and practicability. This dissertation mainly discusses the fuzzy clustering in the field of image segmentation and the fuzzy clustering in the field of image segmentation. The two segmentation methods of active contour model are improved on the basis of the original algorithm, and the following research results are obtained. (1) a fuzzy C mean image segmentation algorithm based on local variation coefficient is proposed. First, the median of all pixels in the local window is used to replace the gray value of the central point pixel, and it is fast generalized. The local gray correlation matrix Sg_ij in the fuzzy C mean (Fast Generalized Fuzzy C-Means, FGFCM) algorithm is modified to improve the algorithm's ability to suppress noise. Then, the local variation coefficient is introduced to reconstruct the local similarity measure between pixels so that it can better control the weight of the center pixels in the neighborhood. Then, the segmentation process is only dependent on the gray level of the image by fast segmentation, which can further improve the efficiency of the algorithm. Compared with the same method, the algorithm improves the image segmentation effect to some extent and has strong robustness to the noise. (2) a kind of local cross entropy measure fuzzy C mean water is proposed. The flat set image segmentation algorithm and its simplified model. First, in view of the greater advantage of the cross entropy criterion in processing noise, it replaces the target function of the FCM_S (Fuzzy C-Means with Spatial Constraints) algorithm by replacing the square error and the criterion, so that the processing can automatically increase or reduce the sample point to be one of them. Secondly, the improved clustering algorithm is incorporated into the variational level set framework, so that the model can be classified accurately. Finally, the weighted iterative method and gradient descending flow method are used to solve the model. The experimental results show that the method can successfully deal with the weak edge relative to the traditional level set algorithm. (3) an active contour model based on local symbol difference and local Gauss distribution fitting energy is proposed. The model is used to introduce local symbol difference (Local Signed Difference, LSD) energy and local Gauss distribution fitting (Local Gaussian Distribution Fittin). G, LGDF) the linear combination of energy terms to construct the evolution force of the level set function, and use the gradient descending flow method to solve the energy functional, so as to drive the curve to the edge of the target. Compared with the traditional active contour model, the new method can correctly extract the target in the gray image image, and the size and position of the initial contour curve. And the shape is more insensitive. (4) a segmentation algorithm based on the regional growth initialization is proposed. Firstly, the adaptive region growth algorithm is used to obtain the rough region of the hippocampus. Secondly, the morphological operation of the results is carried out to eliminate the internal speckles, and the contour tracking operator is further used to get the image segmentation algorithm. In the end, the contour curve is used as a priori information, and the improved level set method is used to drive the contour to the target and stop at the hippocampal boundary. The experimental results show that the results of the proposed algorithm are very close to the results obtained by the expert manual segmentation, and have better accuracy and efficiency.
【學(xué)位授予單位】：西南交通大學(xué)
【學(xué)位級別】：博士
【學(xué)位授予年份】：2016
【分類號】：TP391.41

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 夏菁;張彩明;張小峰;李雪梅;;結(jié)合邊緣局部信息的FCM抗噪圖像分割算法[J];計(jì)算機(jī)輔助設(shè)計(jì)與圖形學(xué)學(xué)報(bào);2014年12期

2 林笑曼;嚴(yán)壯志;蔣皆恢;溫軍玲;;基于三維格子玻爾茲曼模型的海馬結(jié)構(gòu)MRI快速分割[J];生物醫(yī)學(xué)工程學(xué)進(jìn)展;2014年01期

3 于廣婷;李柏林;鄒翎;黃秋菊;;基于改進(jìn)水平集的人腦海馬圖像分割方法[J];計(jì)算機(jī)工程;2013年06期

4 趙姝穎;張丹;覃文軍;楊金柱;潘峰;;基于多尺度水平集的MR圖像海馬區(qū)分割方法[J];儀器儀表學(xué)報(bào);2012年10期

5 王海軍;張圣燕;柳明;馬文來;;融合局部和全局高斯概率信息的圖像分割模型[J];計(jì)算機(jī)工程與應(yīng)用;2014年10期

6 任然;劉宏申;;一種基于Markov隨機(jī)場的圖像分割方法[J];安徽工業(yè)大學(xué)學(xué)報(bào)(自然科學(xué)版);2012年03期

7 紀(jì)則軒;潘瑜;陳強(qiáng);孫權(quán)森;夏德深;;無監(jiān)督模糊C均值聚類自然圖像分割算法[J];中國圖象圖形學(xué)報(bào);2011年05期

8 侯越;;基于灰度直方圖的閾值分割算法[J];硅谷;2010年23期

9 紀(jì)則軒;陳強(qiáng);孫權(quán)森;夏德深;;各向異性權(quán)重的模糊C均值聚類圖像分割[J];計(jì)算機(jī)輔助設(shè)計(jì)與圖形學(xué)學(xué)報(bào);2009年10期

10 溫淑煥;唐英干;;基于Fisher準(zhǔn)則的多閾值圖像分割方法[J];激光與紅外;2008年07期

相關(guān)博士學(xué)位論文 前7條

1 袁建軍;基于偏微分方程圖像分割技術(shù)的研究[D];重慶大學(xué);2012年

2 原野;偏微分方程圖像分割模型研究[D];重慶大學(xué);2012年

3 王艷;圖像分割的偏微分方程研究[D];重慶大學(xué);2012年

4 王曉峰;水平集方法及其在圖像分割中的應(yīng)用研究[D];中國科學(xué)技術(shù)大學(xué);2009年

5 劉軍偉;基于水平集的圖像分割方法研究及其在醫(yī)學(xué)圖像中的應(yīng)用[D];中國科學(xué)技術(shù)大學(xué);2009年

6 何寧;基于活動(dòng)輪廓模型的圖像分割研究[D];首都師范大學(xué);2009年

7 蔡維玲;基于聚類的圖像分割和分類器設(shè)計(jì)的研究[D];南京航空航天大學(xué);2008年

相關(guān)碩士學(xué)位論文 前1條

1 喬陽;基于改進(jìn)遺傳算法的圖像分割方法[D];電子科技大學(xué);2013年

，

本文編號：1997332