【摘要】：隨著計(jì)算機(jī)與通信技術(shù)的快速發(fā)展,圖像和視頻日益成為承載數(shù)據(jù)信息的主要形式。圖像資源出現(xiàn)爆炸式增長(zhǎng),如何通過(guò)計(jì)算機(jī)快速處理和檢索圖像是面臨的重大挑戰(zhàn)。顯著性檢測(cè)技術(shù)是圖像檢索、圖像自適應(yīng)分割、目標(biāo)識(shí)別等計(jì)算機(jī)視覺(jué)領(lǐng)域的重要步驟。人類視覺(jué)系統(tǒng)善于幫助人們?cè)诿鎸?duì)復(fù)雜場(chǎng)景時(shí)搜索到自己感興趣的區(qū)域,模擬人類的視覺(jué)機(jī)制提取與目標(biāo)相關(guān)的顯著區(qū)域,可以為顯著區(qū)域優(yōu)先地分配圖像合成與分析所需的計(jì)算資源,提高計(jì)算機(jī)處理圖像的效率。在研究已有的顯著性檢測(cè)模型的基礎(chǔ)上,總結(jié)出現(xiàn)有模型在提取顯著區(qū)域時(shí)面臨著準(zhǔn)確度不高,提取輪廓不清晰,抗噪能力差等缺點(diǎn),所以研究精確的顯著性檢測(cè)模型變得很重要。本文主要研究工作如下:(1)結(jié)合局部特征對(duì)比突出顯著物體邊緣和全局特征對(duì)比突出內(nèi)部區(qū)域的優(yōu)點(diǎn)本文提出了一種應(yīng)用局部特征和全局特征對(duì)比的顯著性檢測(cè)模型(LGC模型)。該算法首先使用簡(jiǎn)單的線性迭代聚類(Simple Linear Iterative Clustering)分割算法將圖像預(yù)分割為若干緊湊的超像素,選取邊界區(qū)域集并計(jì)算所有超像素的邊界權(quán)重;然后計(jì)算顏色和紋理特征的局部對(duì)比度得到局部顯著圖,利用全局特征的獨(dú)特性,空間分布特性得到全局顯著圖;最后采用求和乘積(Sum and Product)方法將局部和全局顯著圖融合得到最終的顯著圖。在Achanta測(cè)試集上進(jìn)行對(duì)比分析,實(shí)驗(yàn)結(jié)果表明,與其它5種算法相比本文顯著性檢測(cè)算法準(zhǔn)確度更高,具有較大的優(yōu)勢(shì)。(2)將本文提出的顯著性檢測(cè)模型,應(yīng)用在圖像感興趣區(qū)域自動(dòng)分割、內(nèi)容敏感的圖像縮放以及非真實(shí)性渲染應(yīng)用中。實(shí)驗(yàn)結(jié)果表明本文提出的模型相對(duì)于傳統(tǒng)的模型在圖像處理應(yīng)用中的效果更好。
[Abstract]:With the rapid development of computer and communication technology, image and video increasingly become the main form of carrying data information. With the explosive growth of image resources, how to quickly process and retrieve images by computer is a major challenge. Salience detection is an important step in the field of computer vision such as image retrieval, image adaptive segmentation and target recognition. Human visual systems are good at helping people find areas of interest to themselves in the face of complex scenes, and simulate human visual mechanisms to extract salient areas associated with targets. The computational resources needed for image synthesis and analysis can be allocated first for significant regions, and the efficiency of computer processing can be improved. On the basis of studying the existing salience detection models, it is concluded that the models are faced with some shortcomings, such as low accuracy, unclear contour, poor anti-noise ability and so on. So it is very important to study the accurate salience detection model. The main research work of this paper is as follows: (1) combining the advantages of local feature contrast prominent object edge and global feature contrast highlighting internal region this paper proposes a significant application of local feature and global feature contrast. Detection model (LGC model). Firstly, a simple linear iterative clustering (Simple Linear Iterative Clustering) algorithm is used to predivide the image into several compact super-pixels, then the boundary regions are selected and the boundary weights of all super-pixels are calculated. Then the local contrast of color and texture features is calculated and the global salience map is obtained by using the uniqueness of the global feature and the spatial distribution characteristic. Finally, the sum product (Sum and Product) method is used to fuse the local and global salient graphs to obtain the final significant graphs. The experimental results on the Achanta test set show that compared with the other five algorithms, the significance detection algorithm in this paper has higher accuracy and more advantages. (2) the significance detection model proposed in this paper is proposed. It is used in automatic segmentation of region of interest, content sensitive image scaling and non-realistic rendering applications. The experimental results show that the proposed model is more effective than the traditional model in image processing.
【學(xué)位授予單位】：長(zhǎng)沙理工大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2016
【分類號(hào)】：TP391.41

【參考文獻(xiàn)】

相關(guān)期刊論文 前9條

1 羅雅丹;唐振華;覃團(tuán)發(fā);;基于DCT域視覺(jué)顯著性檢測(cè)的圖像縮放算法[J];計(jì)算機(jī)應(yīng)用研究;2016年01期

2 梁淑芬;劉銀華;李立琛;;基于LBP和深度學(xué)習(xí)的非限制條件下人臉識(shí)別算法[J];通信學(xué)報(bào);2014年06期

3 金左輪;韓靜;張毅;柏連發(fā);;基于紋理顯著性的微光圖像目標(biāo)檢測(cè)[J];物理學(xué)報(bào);2014年06期

4 郭迎春;袁浩杰;吳鵬;;基于Local特征和Regional特征的圖像顯著性檢測(cè)[J];自動(dòng)化學(xué)報(bào);2013年08期

5 李崇飛;高穎慧;盧凱;曲智國(guó);;基于相位譜和調(diào)諧幅度譜的顯著性檢測(cè)方法[J];中國(guó)圖象圖形學(xué)報(bào);2012年07期

6 莊凌;莊越挺;吳江琴;葉振超;吳飛;;一種基于稀疏典型性相關(guān)分析的圖像檢索方法[J];軟件學(xué)報(bào);2012年05期

7 張剛;馬宗民;;一種采用Gabor小波的紋理特征提取方法[J];中國(guó)圖象圖形學(xué)報(bào);2010年02期

8 劉麗;匡綱要;;圖像紋理特征提取方法綜述[J];中國(guó)圖象圖形學(xué)報(bào);2009年04期

9 張菁;沈蘭蓀;David Dagan Feng;;基于視覺(jué)感知的圖像檢索的研究[J];電子學(xué)報(bào);2008年03期

相關(guān)博士學(xué)位論文 前3條

1 陳沅濤;圖像視覺(jué)顯著性和改進(jìn)型SVM在圖像分割中的研究[D];南京理工大學(xué);2014年

2 吳金建;基于人類視覺(jué)系統(tǒng)的圖像信息感知和圖像質(zhì)量評(píng)價(jià)[D];西安電子科技大學(xué);2014年

3 張巧榮;視覺(jué)注意計(jì)算模型及其關(guān)鍵技術(shù)研究[D];哈爾濱工程大學(xué);2011年

相關(guān)碩士學(xué)位論文 前1條

1 譚珊;基于顏色對(duì)比和各向異性擴(kuò)散分割的顯著性區(qū)域檢測(cè)[D];大連理工大學(xué);2013年

，

本文編號(hào)：2345951