本文選題：馬爾科夫蒙特卡洛 + 數(shù)據(jù)驅(qū)動(dòng)��； 參考：《南京航空航天大學(xué)》2011年碩士論文

【摘要】：眼底視網(wǎng)膜血管作為人體非創(chuàng)傷觀察的重要器官,其不同程度的變化能夠反映出高血壓、動(dòng)脈硬化等心血管疾病的癥狀,特別當(dāng)與血管相關(guān)的器官發(fā)生病變時(shí),眼底血管的直徑、曲率等特征的改變?cè)谝欢ǔ潭壬峡煞从巢∽兊某潭取９识亢投ㄐ缘刈詣?dòng)分析視網(wǎng)膜血管具有非常重要的臨床應(yīng)用價(jià)值,而視網(wǎng)膜血管分割和提取則是分析血管的首要任務(wù)。 現(xiàn)有多數(shù)視網(wǎng)膜血管分割方法盡管對(duì)非病變的血管圖像具有較好的分割效果,但對(duì)病變圖像的分割效果仍不理想,尤對(duì)光照不均、病灶等敏感。為此,本文提出了一種相對(duì)魯棒的血管分割方法。該方法首次嘗試?yán)糜?jì)算機(jī)視覺中的Top-down和Bottom-up兩種層次化分割框架相結(jié)合實(shí)現(xiàn)視網(wǎng)膜圖像的分割。具體而言,首先在彩色視網(wǎng)膜圖像的綠色通道上利用Curvelet變換進(jìn)行血管增強(qiáng)。然后在貝葉斯統(tǒng)計(jì)框架下,采用可逆跳轉(zhuǎn)的馬爾科夫蒙特卡洛算法搜索參數(shù)空間,從而求得不依賴于初始分割的近似全局最優(yōu)的分割,同時(shí)利用數(shù)據(jù)驅(qū)動(dòng)的均值漂移聚類算法和Canny邊緣檢測(cè)算子來(lái)加速馬爾科夫鏈的動(dòng)態(tài)變化。 本文在MATLAB環(huán)境下,采用標(biāo)準(zhǔn)STARE視網(wǎng)膜圖像庫(kù)中四幅圖像進(jìn)行了實(shí)驗(yàn),實(shí)驗(yàn)結(jié)果表明該方法不僅對(duì)非病變的圖像而且對(duì)病變的圖像都具有較好的魯棒分割效果,并且通過(guò)模式識(shí)別中的沒有免費(fèi)午餐定理在理論上對(duì)該方法進(jìn)行了理論分析。
[Abstract]:The retinal vessels in the fundus of the eye, as an important organ for non-traumatic observation, can reflect the symptoms of cardiovascular diseases such as hypertension, arteriosclerosis and so on, especially when the organs associated with blood vessels are changed. Changes in the diameter and curvature of the fundus vessels can reflect the extent of the lesion to a certain extent. Therefore, quantitative and qualitative automatic analysis of retinal vessels has very important clinical application value. The retinal blood vessel segmentation and extraction is the most important task in the analysis of blood vessels. Although most of the existing retinal blood vessel segmentation methods have good segmentation effect on the non-pathological vascular images, the segmentation effect of the retinal blood vessels image is still not ideal. Especially sensitive to uneven light, lesions, and so on. Therefore, a relatively robust blood vessel segmentation method is proposed in this paper. This method is the first time to use Top-down and Bottom-up in computer vision to realize retinal image segmentation. In particular, the first color retinal image of the green channel using Curvelet transform for vascular enhancement. Then under the Bayesian statistical framework, the reversible jump Markov Monte Carlo algorithm is used to search the parameter space, and the approximate global optimal segmentation independent of the initial segmentation is obtained. At the same time, the data-driven mean shift clustering algorithm and Canny edge detection operator are used to accelerate the dynamic change of Markov chain. The experimental results show that the proposed method has a good robust segmentation effect not only for non-pathological images but also for diseased images, and the theoretical analysis of the method is carried out by using the free lunch theorem in pattern recognition.
【學(xué)位授予單位】：南京航空航天大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2011
【分類號(hào)】：R774.1;R318.0;TP391.41

【參考文獻(xiàn)】

相關(guān)期刊論文 前7條

1 姚暢;陳后金;;病變視網(wǎng)膜圖像血管網(wǎng)絡(luò)的自動(dòng)分割[J];電子學(xué)報(bào);2010年05期

2 王爽,徐亮,李建軍;視網(wǎng)膜微血管異常與心腦血管疾病關(guān)系的流行病學(xué)研究[J];國(guó)外醫(yī)學(xué)(眼科學(xué)分冊(cè));2005年03期

3 隆剛,肖磊,陳學(xué)Oz;Curvelet變換在圖像處理中的應(yīng)用綜述[J];計(jì)算機(jī)研究與發(fā)展;2005年08期

4 金炎芳;張定華;趙歆波;陳志強(qiáng);張東平;;基于混合高斯模型MRF場(chǎng)的CT圖像分割[J];計(jì)算機(jī)應(yīng)用研究;2007年06期

5 戴培山;王博亮;鞠穎;;視網(wǎng)膜血管圖像分割及眼底血管三維重建[J];自動(dòng)化學(xué)報(bào);2009年09期

6 林瑤;田捷;;醫(yī)學(xué)圖像分割方法綜述[J];模式識(shí)別與人工智能;2002年02期

7 李居朋;陳后金;張新媛;;基于先驗(yàn)知識(shí)隨機(jī)游走模型的視網(wǎng)膜血管分割方法[J];中國(guó)生物醫(yī)學(xué)工程學(xué)報(bào);2009年04期

相關(guān)碩士學(xué)位論文 前1條

1 黃勇新;基于眼底影像的計(jì)算機(jī)輔助診斷研究及系統(tǒng)實(shí)現(xiàn)[D];長(zhǎng)春理工大學(xué);2007年

，

本文編號(hào)：1985127