本文選題：基于內(nèi)容的圖像檢索　切入點(diǎn)：草圖檢索　出處：《大連理工大學(xué)》2013年碩士論文　論文類型：學(xué)位論文

【摘要】：隨著互聯(lián)網(wǎng)技術(shù)的發(fā)展,數(shù)字圖像的數(shù)量急劇增長(zhǎng),基于內(nèi)容的圖像檢索技術(shù)引起了國(guó)內(nèi)外學(xué)者廣泛的關(guān)注并取得了顯著的研究成果。近幾年隨著當(dāng)今社會(huì)觸摸屏設(shè)備如平板電腦和智能手機(jī)等的普及,人們開(kāi)始將關(guān)注的重點(diǎn)轉(zhuǎn)移到基于手繪草圖的檢索技術(shù)中。在觸摸屏設(shè)備的幫助下,各個(gè)年齡段、各種繪畫(huà)水平的人都可以輕松繪制出浮現(xiàn)在腦海中的物體,進(jìn)而通過(guò)手繪的線條圖在大量圖片庫(kù)中找到與之形狀類似的圖像。 基于草圖的圖像檢索這一概念最早在20世紀(jì)80年代被提出,但是之后卻一直進(jìn)展較慢,主要是因?yàn)槭掷L草圖中線條的多變性和不確定性使得線條的特征表示、特征匹配以及適合大規(guī)模數(shù)據(jù)庫(kù)的索引結(jié)構(gòu)的建立等方面充滿了困難和挑戰(zhàn)。2010年微軟亞洲研究院提出的可以不依賴關(guān)鍵字,只根據(jù)草圖中物體線條的特征匹配在大規(guī)模圖片數(shù)據(jù)庫(kù)上進(jìn)行實(shí)時(shí)檢索的草圖搜索系統(tǒng)MindFinder再一次引發(fā)了人們對(duì)草圖搜索的研究熱情。 本文提出的基于手繪草圖的圖像檢索系統(tǒng)采用“詞袋模型”來(lái)表示草圖,每幅草圖均可表示為與視覺(jué)字典中的單詞相關(guān)的直方圖。在特征提取過(guò)程我們使用的局部特征描述子是經(jīng)過(guò)改進(jìn)的梯度方向直方圖特征--基于草圖梯度場(chǎng)的梯度方向直方圖(GF-HoG),該特征能夠有效地表示由線條構(gòu)成的草圖；在構(gòu)建視覺(jué)字典時(shí)我們采用分層K-means聚類算法,該聚類算法與傳統(tǒng)的K-means聚類算法相比能獲得更精確的聚類結(jié)果。最后通過(guò)比較輸入草圖與圖像庫(kù)中圖像之間的余弦相似性實(shí)現(xiàn)庫(kù)內(nèi)檢索過(guò)程,通過(guò)多類SVM分類器可以得到輸入草圖所屬類別的關(guān)鍵字,將關(guān)鍵字送至搜索引擎能夠?qū)崿F(xiàn)在線檢索。我們?cè)贓itz提供的手繪草圖數(shù)據(jù)庫(kù)和Microsoft Office文檔中提供的形狀圖數(shù)據(jù)庫(kù)中進(jìn)行了一系列實(shí)驗(yàn),實(shí)驗(yàn)結(jié)果表明本論文提出的手繪草圖檢索算法與MindFinder和Eitz的草圖檢索算法相比效果更加顯著。
[Abstract]:With the development of Internet technology, the number of digital images has increased dramatically. Content-based image retrieval technology has attracted wide attention from scholars at home and abroad and achieved remarkable research results. In recent years, with the popularity of touch screen devices such as tablets and smart phones, People are starting to shift their focus to hand-sketch-based retrieval technology. With the help of touchscreen devices, people of all ages and levels of painting can easily draw objects that come to mind. And then through the hand-drawn line map in a large number of photo library to find the shape of the image. The concept of Sketch-based Image Retrieval was first proposed in the 1980s, but the progress has been slow since then, mainly because of the variability and uncertainty of the lines in the hand-drawn sketches. Feature matching and the creation of index structures suitable for large-scale databases are fraught with difficulties and challenges. The sketch search system (MindFinder), which only performs real-time retrieval based on the feature matching of objects and lines in sketches, has once again aroused people's enthusiasm for sketch search. This paper presents an image retrieval system based on hand-drawn sketches, which uses a "word bag model" to represent sketches. Each sketch can be represented as a histogram associated with a word in a visual dictionary. The local feature descriptor we use in the feature extraction process is an improved gradient direction histogram feature-a gradient based on the gradient field of the sketch. Direction histogram (GF-HoG), which can effectively represent sketches composed of lines; In constructing visual dictionary, we adopt hierarchical K-means clustering algorithm. Compared with the traditional K-means clustering algorithm, this clustering algorithm can obtain more accurate clustering results. Finally, the retrieval process in the database is realized by comparing the cosine similarity between the input sketches and the images in the image database. The keywords of the category to which the input sketch belongs can be obtained by the multi-class SVM classifier. Sending keywords to search engines enables online retrieval. We have done a series of experiments in the sketching database provided by Eitz and the shape map database provided in Microsoft Office documents. Experimental results show that the proposed hand-drawn sketch retrieval algorithm is more effective than that of MindFinder and Eitz.
【學(xué)位授予單位】：大連理工大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2013
【分類號(hào)】：TP391.41

【參考文獻(xiàn)】

相關(guān)期刊論文 前9條

1 王千;王成;馮振元;葉金鳳;;K-means聚類算法研究綜述[J];電子設(shè)計(jì)工程;2012年07期

2 金微;陳慧萍;;基于分層聚類的k-means算法[J];河海大學(xué)常州分校學(xué)報(bào);2007年01期

3 陳劍峗,老松揚(yáng),吳玲達(dá);基于內(nèi)容的圖像檢索的發(fā)展最新趨勢(shì)[J];計(jì)算機(jī)工程與應(yīng)用;2002年10期

4 陳峗;沈一帆;;基于詞匯樹(shù)的圖片搜索[J];計(jì)算機(jī)工程;2010年06期

5 唐發(fā)明,王仲東,陳綿云;支持向量機(jī)多類分類算法研究[J];控制與決策;2005年07期

6 茍博;黃賢武;;支持向量機(jī)多類分類方法[J];數(shù)據(jù)采集與處理;2006年03期

7 向培素;;聚類算法綜述[J];西南民族大學(xué)學(xué)報(bào)(自然科學(xué)版);2011年S1期

8 蘇曉珂,虎曉紅,蘭洋;基于內(nèi)容的圖像檢索技術(shù)綜述[J];信陽(yáng)師范學(xué)院學(xué)報(bào)(自然科學(xué)版);2005年04期

9 馬繼紅;師軍;;基于內(nèi)容的圖像檢索技術(shù)研究[J];鄭州輕工業(yè)學(xué)院學(xué)報(bào)(自然科學(xué)版);2009年04期

相關(guān)會(huì)議論文 前1條

1 龔健;費(fèi)廣正;石民勇;曹瑋;;基于手繪草圖輪廓檢索的簡(jiǎn)筆繪圖系統(tǒng)[A];'2008系統(tǒng)仿真技術(shù)及其應(yīng)用學(xué)術(shù)會(huì)議論文集[C];2008年

相關(guān)碩士學(xué)位論文 前1條

1 夏榮進(jìn);基于形狀上下文的圖像內(nèi)容檢索方法研究[D];華中科技大學(xué);2011年

，

本文編號(hào)：1650575