發(fā)布時(shí)間：2018-06-04 05:17

  本文選題：網(wǎng)格分割 + 網(wǎng)格譜聚類(lèi)��； 參考：《吉林大學(xué)》2016年博士論文

【摘要】：得益于計(jì)算機(jī)科學(xué)和相關(guān)數(shù)學(xué)理論的進(jìn)步與完善,圖形圖像處理已成為當(dāng)今非�；钴S的研究方向之一。其中,圖形圖像分割問(wèn)題一直是該領(lǐng)域中的重要研究課題。經(jīng)過(guò)多年的研究與發(fā)展,圖形圖像分割技術(shù)已被廣泛應(yīng)用于計(jì)算機(jī)動(dòng)畫(huà)、醫(yī)學(xué)影像處理、虛擬現(xiàn)實(shí)、計(jì)算可視化等多個(gè)領(lǐng)域。在許多圖像處理工作中,都需要對(duì)圖像中的某些區(qū)域進(jìn)行提取,我們可以借助圖像分割技術(shù)對(duì)像素進(jìn)行劃分,將目標(biāo)區(qū)域從背景中分離出來(lái)。由于圖像分割的結(jié)果對(duì)后續(xù)的視覺(jué)任務(wù)有直接影響,這使得圖像分割成為從底層圖像處理進(jìn)入到圖像識(shí)別與理解的關(guān)鍵步驟。人類(lèi)可以準(zhǔn)確的將圖像中的目標(biāo)區(qū)域分離出來(lái),但對(duì)于計(jì)算機(jī)這卻并不是一件容易的事情。多數(shù)情況下受圖像自身質(zhì)量、以及圖像內(nèi)容的復(fù)雜性和多樣性等因素的影響,使計(jì)算機(jī)很難按照人的理解對(duì)圖像進(jìn)行分割。目前的圖像分割方法多是以圖像中各區(qū)域的相似性,或特征差異度作為判斷準(zhǔn)則,將圖像分成互不相交的若干區(qū)域,卻很少把人類(lèi)視覺(jué)特性應(yīng)用于分割的過(guò)程中,致使產(chǎn)生的分割結(jié)果通常與人的視覺(jué)感知相差甚遠(yuǎn)。因此,如何將視覺(jué)特性與圖像分割技術(shù)相結(jié)合,產(chǎn)生更符合人類(lèi)視覺(jué)感知的分割結(jié)果,仍然是圖像處理及相關(guān)領(lǐng)域中值得深入研究的課題。隨著數(shù)據(jù)獲取設(shè)備的進(jìn)步以及建模技術(shù)的不斷發(fā)展,三維圖形數(shù)據(jù)已經(jīng)成為一種新的數(shù)字媒體表示形式,對(duì)于三維模型的分析與處理也成為計(jì)算機(jī)圖形學(xué)領(lǐng)域的研究熱點(diǎn)。與圖像分割問(wèn)題一樣,人們?nèi)匀幌Ｍ梢越柚祟?lèi)視覺(jué)特性及相關(guān)理論對(duì)網(wǎng)格模型進(jìn)行“有意義”的分割,得到多個(gè)具有視覺(jué)意義或物理意義的部件,以便于從更高層次上對(duì)模型進(jìn)行理解。但通常情況下,人們對(duì)于“有意義”部件的定義是非常主觀的,而且在不同的應(yīng)用背景下,對(duì)于“有意義”分割的定義也有所差異。此外與二維圖像數(shù)據(jù)相比較,三維模型除了幾何屬性外,還包含復(fù)雜的空間信息與拓?fù)湫畔?這使得三維模型的分割問(wèn)題更具挑戰(zhàn)性。因此,如何利用人類(lèi)視覺(jué)特性,產(chǎn)生更加符合視覺(jué)感知的網(wǎng)格分割結(jié)果仍是值得進(jìn)一步研究的課題。鑒于如何產(chǎn)生更加符合視覺(jué)感知的分割結(jié)果是圖像分割與三維模型分割共同關(guān)注的問(wèn)題之一,本文從人類(lèi)視覺(jué)特性的角度出發(fā),對(duì)圖像分割與網(wǎng)格分割問(wèn)題進(jìn)行研究,并分別提出新的圖像分割算法與網(wǎng)格分割算法。本文主要研究工作包括以下幾點(diǎn)：(1)提出一種符合人類(lèi)視覺(jué)特性的圖像自適應(yīng)閾值分割方法(Visual consistent adaptive thresholding method, VCA method)。傳統(tǒng)閾值分割方法在分割過(guò)程中只考慮了圖像灰度特性與空間信息,而忽略了視覺(jué)對(duì)于分割結(jié)果的影響。與傳統(tǒng)閾值分割方法不同,我們的方法將閾值選擇過(guò)程與人類(lèi)視覺(jué)特性相融合,提出一種視覺(jué)一致的自適應(yīng)圖像閡值分割方法。首先根據(jù)像素的灰度信息構(gòu)建兩幅子圖；然后根據(jù)人類(lèi)視覺(jué)特性定義目標(biāo)函數(shù),定量刻畫(huà)圖像中的視覺(jué)信息；通過(guò)對(duì)目標(biāo)函數(shù)優(yōu)化求解,得到每幅子圖的全局最優(yōu)閾值；最后再利用圖像的局部特性,進(jìn)行局部自適應(yīng)閾值操作得到最終的閡值分割結(jié)果。由于在閾值分割的過(guò)程中,我們利用人類(lèi)視覺(jué)特性對(duì)前景與背景進(jìn)行自動(dòng)分離,使得分割后的二值圖像獲得了較好的視覺(jué)效果,其整體的視覺(jué)質(zhì)量更符合人類(lèi)視覺(jué)感知。(2)提出一種新的選取網(wǎng)格模型關(guān)鍵點(diǎn)的方法,我們稱(chēng)之為種子點(diǎn),并在此基礎(chǔ)上提出一種有意義的網(wǎng)格分割方法。首先找到網(wǎng)格模型中的尖銳特征區(qū)域,選出每個(gè)區(qū)域中最為顯著的網(wǎng)格頂點(diǎn)構(gòu)建候選點(diǎn)集合；用于分割的種子點(diǎn)是特征點(diǎn)集合的子集,通過(guò)最大化頂點(diǎn)集合之間的差異度對(duì)特征點(diǎn)集合進(jìn)行篩選,從而得到網(wǎng)格模型的種子點(diǎn)集合；在此基礎(chǔ)上,利用種子點(diǎn)集合對(duì)網(wǎng)格模型進(jìn)行分割；根據(jù)視覺(jué)理論中的最小準(zhǔn)則可知,人們通常將模型中的凹區(qū)域看成潛在的分割邊界,為此我們利用網(wǎng)格模型的幾何屬性定義網(wǎng)格頂點(diǎn)間的距離函數(shù),該函數(shù)由弧長(zhǎng),角距離和修正項(xiàng)三部分組成；最后通過(guò)對(duì)網(wǎng)格頂點(diǎn)進(jìn)行聚類(lèi),得到視覺(jué)上有意義的分割結(jié)果。(3)提出一種基于視覺(jué)顯著性與譜聚類(lèi)的網(wǎng)格分割方法。我們將三維模型在原空間中的分割問(wèn)題轉(zhuǎn)化為譜空間的聚類(lèi)問(wèn)題。通過(guò)將視覺(jué)顯著性與譜聚類(lèi)過(guò)程相結(jié)合,生成有視覺(jué)意義的網(wǎng)格分割結(jié)果。首先根據(jù)視覺(jué)理論中的最小值規(guī)則制定多個(gè)判斷準(zhǔn)則以確定網(wǎng)格凹區(qū)域；然后根據(jù)網(wǎng)格的顯著性來(lái)刻畫(huà)頂點(diǎn)間的關(guān)聯(lián)度,從而定義出網(wǎng)格模型的Laplacian矩陣；通過(guò)計(jì)算矩陣的特征向量,我們可以對(duì)原網(wǎng)格模型進(jìn)行k維譜空間嵌入,從而將模型在原空間域中的分割問(wèn)題轉(zhuǎn)化為譜空間的聚類(lèi)問(wèn)題：最后通過(guò)分析網(wǎng)格的顯著性確定每一類(lèi)的初始聚類(lèi)中心,并利用高斯混合模型(Gaussian Mixture Model, GMM)聚類(lèi)方法對(duì)嵌入空間的網(wǎng)格頂點(diǎn)進(jìn)行聚類(lèi),最終得到有視覺(jué)意義的網(wǎng)格分割結(jié)果。實(shí)驗(yàn)結(jié)果表明該算法可以得到視覺(jué)上有意義的分割結(jié)果,特別是對(duì)于凹凸特征明顯,以及具有核心部件和分支結(jié)構(gòu)的模型,該方法可以產(chǎn)生較好的視覺(jué)結(jié)果。
[Abstract]:Because of the progress and perfection of computer science and related mathematics theory, graphic image processing has become one of the most active research directions. The image segmentation problem has always been an important research topic in this field. After years of research and development, graphic image segmentation technology has been widely used in computer animation, Medical image processing, virtual reality, computing visualization and many other fields. In many image processing work, some areas of the image need to be extracted. We can divide the pixels by image segmentation technology and separate the target area from the background. This makes the image segmentation a key step in the image recognition and understanding from the underlying image processing. Human can accurately separate the target area from the image, but it is not an easy thing for the computer. In most cases, the quality of the image itself, and the complexity and diversity of the image content are in most cases. The influence of other factors makes it difficult for the computer to divide the image according to human understanding. At present, the image segmentation method is mostly based on the similarity of each region in the image, or the difference of feature as the criterion, and divides the image into several regions which are not intersected with each other, but rarely applies the human visual consciousness to the process of segmentation. The segmentation results are usually far from the human visual perception. Therefore, how to combine the visual characteristics with the image segmentation technology to produce the segmentation results more consistent with the human visual perception is still a subject worth studying in the image processing and related fields. With the progress of data acquisition and the continuous development of modeling technology, three Graphic data has become a new form of digital media representation, and the analysis and processing of 3D model has become a hot topic in the field of computer graphics. Like image segmentation, people still want to use human visual characteristics and related theories to make "meaningful" segmentation of the grid model, and get many of them. A component with visual meaning or physical meaning to facilitate understanding of the model at a higher level. However, in general, the definition of a "meaningful" component is very subjective, and the definition of "meaningful" segmentation is also different in different application backgrounds. In addition, compared with the two-dimensional image data, three In addition to geometric properties, dimensional models also contain complex spatial and topological information, which makes the segmentation of 3D models more challenging. Therefore, how to make use of human visual characteristics to produce mesh segmentation results more consistent with visual perception is still a subject worthy of further study. The segmentation results are one of the issues of common concern for image segmentation and 3D model segmentation. From the perspective of human visual characteristics, this paper studies the problem of image segmentation and mesh segmentation, and proposes new image segmentation algorithms and mesh segmentation algorithms. The main research work includes the following points: (1) a conformation is proposed. The image adaptive threshold segmentation method (Visual consistent adaptive thresholding method, VCA method) for human visual characteristics. The traditional threshold segmentation method only takes into account the image grayscale characteristics and spatial information in the segmentation process, but neglects the effect of vision on the segmentation results. Our method is different from the traditional threshold segmentation method. Combining the threshold selection process with the human visual characteristics, a vision consistent adaptive image segmentation method is proposed. First, two subgraphs are constructed according to the pixel gray information, then the target function is defined according to the human visual characteristics, and the visual information in the image is quantitatively depicted. The global optimal threshold of the amplitude subgraph; finally, using the local characteristics of the image, the final threshold segmentation results are obtained by local adaptive threshold operation. In the process of threshold segmentation, we use the human visual characteristics to automatically separate the foreground and the background, and make the two value images after the score cut better visual effect, The visual quality of the whole is more in line with human visual perception. (2) a new method of selecting key points of the grid model is proposed. We call it the seed point. On this basis, we propose a meaningful mesh segmentation method. First, we find the sharp feature area in the grid model, and select the most significant grid vertex in each area. The seed point set for the segmentation is a subset of the set of feature points. The seed point set of the grid model is obtained by selecting the set of the feature points by the difference degree of the maximum vertex sets. On this basis, the mesh model is segmented by the seed set. According to the minimum criterion in the visual theory, It is known that the concave region in the model is usually considered as a potential segmentation boundary, so we use the geometric attributes of the grid model to define the distance function between the vertices of the grid. This function is composed of three parts: arc length, angular distance and correction term. Finally, by clustering the vertices of the grid, the visual meaningful segmentation results are obtained. (3) proposed A mesh segmentation method based on visual significance and spectral clustering. We transform the segmentation problem in the original space into the clustering problem in the spectral space. By combining the visual significance with the spectral clustering process, the results of the mesh segmentation with visual meaning are generated. The criterion is determined to determine the concave area of the grid, and then the correlation degree between the vertices is depicted according to the significance of the grid, and the Laplacian matrix of the mesh model is defined. By calculating the eigenvectors of the matrix, we can embed the K dimensional space of the original mesh model to transform the segmentation problem into the spectrum in the original space domain. Clustering problem of space: finally, the initial clustering center of each class is determined by analyzing the saliency of the grid, and the Gauss hybrid model (Gaussian Mixture Model, GMM) clustering method is used to cluster the mesh vertices of the embedded space. Finally, the results of the mesh segmentation with visual sense are obtained. The experimental results show that the algorithm can be viewed. The results of meaningful segmentation, especially the obvious characteristics of concave and convex, and the model with core components and branch structures, can produce better visual results.
【學(xué)位授予單位】：吉林大學(xué)
【學(xué)位級(jí)別】：博士
【學(xué)位授予年份】：2016
【分類(lèi)號(hào)】：TP391.41

【相似文獻(xiàn)】

相關(guān)期刊論文 前10條

1 郭亦霖;;視覺(jué)特性與信息傳播[J];甘肅科技縱橫;2010年05期

2 孟海山;;人的視覺(jué)特性與電視[J];電視技術(shù);1990年04期

3 廖斌;許剛;劉春穎;;基于高級(jí)視覺(jué)特性的感興趣區(qū)域判定算法[J];計(jì)算機(jī)應(yīng)用;2006年12期

4 朱自蘭;萬(wàn)靜華;李章兵;;基于視覺(jué)特性的地毯圖案色彩量化方法[J];南昌大學(xué)學(xué)報(bào)(工科版);2006年04期

5 秦川;王朔中;張新鵬;;一種基于視覺(jué)特性的圖像摘要算法[J];中國(guó)圖象圖形學(xué)報(bào);2006年11期

6 趙立龍;顧澤蒼;方志良;母國(guó)光;;一種基于視覺(jué)特性及形態(tài)網(wǎng)屏編碼的紙介質(zhì)信息防偽方法[J];光電子.激光;2008年11期

7 鞏凌青;秦志遠(yuǎn);耿利川;鄒瑜;;基于視覺(jué)特性的影像增強(qiáng)算法研究[J];海洋測(cè)繪;2009年02期

8 張新鵬,王朔中,張開(kāi)文;基于視覺(jué)特性的多比特量化水印方案[J];光電子·激光;2003年11期

9 劉建東;陳桂強(qiáng);余有明;田野;;基于視覺(jué)特性及低位替換優(yōu)化的信息隱藏方法[J];計(jì)算機(jī)工程;2007年08期

10 于新波;趙輝;孫暢;;基于視覺(jué)特性的視頻壓縮預(yù)處理方法的研究[J];電氣電子教學(xué)學(xué)報(bào);2008年01期

相關(guān)會(huì)議論文 前3條

1 劉文兆;費(fèi)廣正;湛永松;石民勇;;基于視覺(jué)特性的多義人臉合成系統(tǒng)[A];圖像圖形技術(shù)研究與應(yīng)用2009——第四屆圖像圖形技術(shù)與應(yīng)用學(xué)術(shù)會(huì)議論文集[C];2009年

2 倪國(guó)強(qiáng);蔓君;胡宏清;;基于生物視覺(jué)特性的真實(shí)影像再現(xiàn)技術(shù)及其前景展望[A];中國(guó)光學(xué)學(xué)會(huì)2006年學(xué)術(shù)大會(huì)論文摘要集[C];2006年

3 李文育;董浩亮;;數(shù)碼樣張辯色閾值與人眼顏色視覺(jué)特性分析[A];顏色科學(xué)與技術(shù)——2012第二屆中國(guó)印刷與包裝學(xué)術(shù)會(huì)議論文摘要集[C];2012年

相關(guān)博士學(xué)位論文 前1條

1 焦雪;基于視覺(jué)特性的圖形圖像分割算法研究[D];吉林大學(xué);2016年

相關(guān)碩士學(xué)位論文 前10條

1 趙曉霞;山區(qū)高速公路駕駛員視覺(jué)信息認(rèn)知研究[D];北京建筑大學(xué);2015年

2 孟凡城;公交車(chē)駕駛員安全駕駛視覺(jué)特性研究[D];青島理工大學(xué);2015年

3 王俊翔;城市道路環(huán)境下駕駛員應(yīng)激響應(yīng)視覺(jué)特性[D];長(zhǎng)安大學(xué);2015年

4 鄂明順;基于視覺(jué)特性的老年產(chǎn)品數(shù)字界面交互設(shè)計(jì)研究[D];南京理工大學(xué);2015年

5 查歡歡;基于現(xiàn)代實(shí)木椅子的徑向木紋視覺(jué)特性研究[D];南京林業(yè)大學(xué);2015年

6 吳家欽;植物作為景觀材料的視覺(jué)特性研究[D];北京林業(yè)大學(xué);2004年

7 張雪;基于視覺(jué)特性的壓縮感知圖像/視頻編碼研究[D];太原科技大學(xué);2013年

8 王錦;基于視覺(jué)特性的密寫(xiě)及密寫(xiě)分析研究[D];西南交通大學(xué);2010年

9 劉俊敏;基于蛙眼視覺(jué)特性的運(yùn)動(dòng)目標(biāo)分析研究[D];湖南大學(xué);2013年

10 付蘆靜;基于視覺(jué)特性的印刷質(zhì)量在線(xiàn)檢測(cè)技術(shù)研究[D];江南大學(xué);2014年

，

本文編號(hào)：1976121