本文選題：圖像分割　切入點(diǎn)：Otsu方法　出處：《太原科技大學(xué)》2017年碩士論文　論文類型：學(xué)位論文

【摘要】：圖像分割在數(shù)字圖像處理、模式識(shí)別等領(lǐng)域是非常重要的研究課題,尤其在醫(yī)學(xué)領(lǐng)域中發(fā)揮著越來越大的作用。由于傳統(tǒng)的醫(yī)學(xué)圖像分割基本上是基于人工分割,分割結(jié)果往往無法令人滿意,而且費(fèi)時(shí)費(fèi)力。因此,如何將醫(yī)學(xué)圖像實(shí)現(xiàn)自動(dòng)分割,并以此為基礎(chǔ)對(duì)病灶圖像進(jìn)行識(shí)別等,一直是醫(yī)學(xué)圖像處理的研究難點(diǎn)和重點(diǎn)。本文針對(duì)未考慮灰度信息分布不均勻而使得一些細(xì)節(jié)未能得到良好分割的情況,將主動(dòng)輪廓法和最大類間方差Otsu方法相結(jié)合來進(jìn)行分割;在此基礎(chǔ)上,考慮病變區(qū)域紋理特征和形狀特征信息,通過支持向量機(jī)SVM對(duì)其病灶圖像進(jìn)行了分類識(shí)別處理,主要內(nèi)容如下:(1)醫(yī)學(xué)圖像區(qū)域分割研究。針對(duì)各種具有復(fù)雜的器官與組織的醫(yī)學(xué)圖像中常常未考慮到灰度信息分布不均勻的情況,本文將Otsu方法融入到水平集Chan-Vese模型中,構(gòu)造新的能量函數(shù),對(duì)分割圖像進(jìn)行目標(biāo)輪廓演化處理,在保留了Chan-Vese模型優(yōu)點(diǎn)的情況下,融入了圖像分布的類間方差信息,從而實(shí)現(xiàn)灰度信息分布不均勻醫(yī)學(xué)圖像分割。采用兩個(gè)數(shù)據(jù)集提供的人腦圖像數(shù)據(jù)進(jìn)行實(shí)驗(yàn),結(jié)果表明所提方法在相似性度量和正誤率度量方面,相比其他同類方法都有明顯的優(yōu)勢(shì)。(2)病變圖像特征提取與識(shí)別研究。針對(duì)醫(yī)學(xué)圖像病變區(qū)域信息復(fù)雜,使用單一的紋理特征分類效果不佳的問題,本文首先在常用的紋理特征基礎(chǔ)上,融入Hough變換和不變矩兩個(gè)形狀特征,以考慮旋轉(zhuǎn)、平移等畸變帶來的圖像失真影響;然后對(duì)這些非線性分布融合信息線性化處理,通過支持向量機(jī)SVM對(duì)其進(jìn)行分類,得到病變圖像與正常圖像的識(shí)別;最后,采用某醫(yī)院提供的圖像進(jìn)行紋理特征和形狀特征提取,進(jìn)而進(jìn)行SVM分類實(shí)驗(yàn),實(shí)驗(yàn)結(jié)果表明,分類準(zhǔn)確率有所提高。
[Abstract]:Image segmentation is a very important research topic in the fields of digital image processing and pattern recognition, especially in the field of medicine. The segmentation results are often unsatisfactory and time-consuming. Therefore, how to segment the medical image automatically and recognize the focus image based on it, etc. It has always been a difficult and important point in medical image processing. In this paper, some details are not well segmented because the uneven distribution of gray information is not considered. The active contour method and the maximum inter-class variance (Otsu) method are combined to segment the lesions. On this basis, considering the texture and shape features of the lesion region, the focus images are classified and identified by support vector machine (SVM). The main contents are as follows: (1) Research on region segmentation of medical image. In view of the non-uniform distribution of gray information in various medical images with complex organs and tissues, the Otsu method is incorporated into the level set Chan-Vese model. A new energy function is constructed to process the target contour evolution of the segmented image. With the advantages of the Chan-Vese model, the inter-class variance information of the image distribution is incorporated. In order to realize the segmentation of medical image with uneven distribution of gray information, the human brain image data provided by two data sets are used to carry out experiments. The results show that the proposed method is in the aspect of similarity measurement and correct and false rate measurement. Compared with other similar methods, it has obvious advantages in feature extraction and recognition of pathological image. Aiming at the problem of complex information of lesion region in medical image, the classification effect of single texture feature is not good. In this paper, based on the commonly used texture features, Hough transform and moment invariant feature are incorporated to consider the distortion effect caused by the distortion such as rotation and translation, and then the nonlinear distribution fusion information is linearized. It is classified by support vector machine (SVM) to obtain the recognition of pathological image and normal image. Finally, the texture feature and shape feature are extracted from the image provided by a hospital, and then the experiment of SVM classification is carried out. The experimental results show that, The accuracy of classification is improved.
【學(xué)位授予單位】：太原科技大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類號(hào)】：R310;TP391.41

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 時(shí)永剛;譚繼雙;劉志文;;基于圖割和水平集的腎臟醫(yī)學(xué)圖像分割[J];計(jì)算機(jī)科學(xué);2016年07期

2 吳宇翔;龔濤;梁文宇;;基于改進(jìn)的免疫模糊聚類方法的醫(yī)學(xué)圖像分割[J];微型機(jī)與應(yīng)用;2016年06期

3 宋斌;楊恢先;曾金芳;譚正華;李翠菊;;基于平均中值離差的2維最小誤差閾值分割法[J];激光技術(shù);2015年05期

4 張瓊敏;張勁;王敏堂;何凌;門乙;魏駿;黃華;;基于增強(qiáng)梯度水平集的頭頸部腫瘤分割[J];生物醫(yī)學(xué)工程學(xué)雜志;2015年04期

5 江貴平;秦文健;周壽軍;王昌淼;;醫(yī)學(xué)圖像分割及其發(fā)展現(xiàn)狀[J];計(jì)算機(jī)學(xué)報(bào);2015年06期

6 張榮國;劉小君;董磊;李富萍;劉q;;物體輪廓形狀超像素圖割快速提取方法[J];模式識(shí)別與人工智能;2015年04期

7 吳春俐;張憲林;聶榮;丁山;;基于小波變換的改進(jìn)DDGVF醫(yī)學(xué)圖像分割算法[J];東北大學(xué)學(xué)報(bào)(自然科學(xué)版);2014年06期

8 武園;葛玉榮;;一種基于腦部腫瘤MR圖像的分割方法[J];電子設(shè)計(jì)工程;2014年10期

9 劉金;金煒東;;3維自適應(yīng)最小誤差閾值分割法[J];中國圖象圖形學(xué)報(bào);2013年11期

10 曾麗娟;張華;彭洪云;彭向東;;基于支持向量機(jī)的肛腸病癥識(shí)別算法研究[J];計(jì)算機(jī)仿真;2013年11期

相關(guān)碩士學(xué)位論文 前1條

1 曾宇凡;基于醫(yī)學(xué)圖像的肝纖維化計(jì)算機(jī)輔助診斷研究[D];廣西大學(xué);2013年

，

本文編號(hào)：1598461