發(fā)布時間：2018-07-31 14:37

【摘要】：圖像檢索已成為獲取信息的重要手段之一,如何快速準確地從海量圖像中獲取所需內(nèi)容成為圖像檢索發(fā)展的主要瓶頸。因此本文主要研究如何選擇圖像特征,設(shè)計檢索算法,構(gòu)建圖像檢索系統(tǒng)和提升系統(tǒng)性能。本文的工作可以分為圖像特征分析、檢索算法設(shè)計和基于Hadoop平臺的并行化實現(xiàn)三個部分。本文設(shè)計實現(xiàn)了一種基于顏色相關(guān)圖和SIFT特征的圖像檢索算法,在此基礎(chǔ)上利用DBSCAN聚類算法把SIFT特征提取和匹配限定在一定范圍內(nèi),并借助Hadoop大數(shù)據(jù)處理框架構(gòu)建了基于內(nèi)容的圖像檢索系統(tǒng)。本文首先梳理了圖像檢索技術(shù)的發(fā)展及成果,探討了基于文本、內(nèi)容、高層語義的圖像檢索技術(shù),分析了他們的優(yōu)缺點和適用場景。其次,為了提高檢索的準確度,本文選擇融合顏色自相關(guān)圖和SIFT特征。在此基礎(chǔ)上,本文利用基于密度的DBSCAN聚類算法對64維顏色特征進行聚類,找到與樣例圖像距離最近的類簇,然后在這個類簇范圍內(nèi)進行SIFT特征的提取和匹配以降低算法時間復(fù)雜度�？紤]到當(dāng)兩張圖片的特征點間歐氏距離整體偏大時,傳統(tǒng)的基于SIFT特征點匹配比例的相似性度量方式會丟失一定的空間信息,本文使用SIFT特征匹配點的平均歐氏距離作為相似性度量依據(jù)。最后本文實現(xiàn)了基于MapReduce的綜合特征提取和匹配,并利用AGD-DBSCAN算法中尋找數(shù)據(jù)集自適應(yīng)鄰域半徑和鄰域最小點數(shù)的思想,實現(xiàn)了 DBSCAN聚類過程的MapReduce化。本文分別對算法的查準率、查全率和Hadoop框架下的系統(tǒng)加速比、效率、擴展率做了評估,驗證了本文算法的可用性和可擴展性。
[Abstract]:Image retrieval has become one of the important means to obtain information. How to quickly and accurately obtain the required content from massive images has become the main bottleneck in the development of image retrieval. Therefore, this paper mainly studies how to select image features, design retrieval algorithm, build image retrieval system and improve system performance. The work of this paper can be divided into three parts: image feature analysis, retrieval algorithm design and parallel implementation based on Hadoop platform. In this paper, an image retrieval algorithm based on color correlation graph and SIFT feature is designed and implemented. On this basis, SIFT feature extraction and matching are limited to a certain range by using DBSCAN clustering algorithm. A content-based image retrieval system is constructed with the help of Hadoop big data processing framework. This paper firstly combs the development and achievement of image retrieval technology, discusses the image retrieval technology based on text, content and high-level semantics, and analyzes their advantages and disadvantages and applicable scenarios. Secondly, in order to improve the accuracy of retrieval, this paper selects the fusion of color autocorrelation and SIFT features. On this basis, we use the density-based DBSCAN clustering algorithm to cluster the 64-dimensional color features, and find the cluster closest to the sample image. Then the SIFT features are extracted and matched in this cluster to reduce the time complexity of the algorithm. Considering that when the Euclidean distance between the feature points of two images is relatively large, the traditional similarity measurement method based on the matching ratio of SIFT feature points will lose some spatial information. In this paper, the average Euclidean distance of SIFT feature matching points is used as the basis of similarity measurement. Finally, this paper realizes the synthesis feature extraction and matching based on MapReduce, and makes use of the idea of finding the adaptive neighborhood radius and the minimum number of neighborhood points in the AGD-DBSCAN algorithm to realize the MapReduce of the DBSCAN clustering process. In this paper, the recall rate, recall rate and system speedup, efficiency and expansion rate of the algorithm under Hadoop framework are evaluated, and the availability and extensibility of the algorithm are verified.
【學(xué)位授予單位】：東南大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2017
【分類號】：TP391.41

【參考文獻】

相關(guān)期刊論文 前10條

1 鄭啟財;曾智勇;池燕玲;;改進的基于顏色和SIFT特征的圖像檢索方法[J];計算機系統(tǒng)應(yīng)用;2015年11期

2 陳勇平;郭文靜;王正;;基于顏色直方圖的木材單板圖像檢索技術(shù)研究[J];南京林業(yè)大學(xué)學(xué)報(自然科學(xué)版);2015年05期

3 郭樹旭;趙靜;李雪妍;;基于中心-輪廓距離特征統(tǒng)計的形狀表示方法[J];電子與信息學(xué)報;2015年06期

4 孫延維;雷建軍;蘇丹;;綜合顏色塊的直方圖圖像檢索算法[J];華中師范大學(xué)學(xué)報(自然科學(xué)版);2015年02期

5 張永庫;李云峰;孫勁光;;基于改進顏色聚合向量與貢獻度聚類的圖像檢索算法[J];計算機科學(xué);2015年02期

6 謝莉;成運;曾接賢;余勝;;基于顏色和梯度方向共生直方圖的圖像檢索[J];計算機工程與應(yīng)用;2016年10期

7 張永庫;李云峰;孫勁光;;綜合顏色和形狀特征聚類的圖像檢索[J];計算機應(yīng)用;2014年12期

8 顧曉東;楊誠;;新的顏色相似度衡量方法在圖像檢索中的應(yīng)用[J];儀器儀表學(xué)報;2014年10期

9 沈新寧;王小龍;杜建洪;;基于顏色自相關(guān)圖和互信息的圖像檢索算法[J];計算機工程;2014年02期

10 董傲霜;宋宏亮;;基于SIFT特征和顏色融合的圖像檢索方法[J];吉林大學(xué)學(xué)報(工學(xué)版);2013年S1期

相關(guān)碩士學(xué)位論文 前2條

1 姜文;基于Hadoop平臺的數(shù)據(jù)分析和應(yīng)用[D];北京郵電大學(xué);2011年

2 王炬;多媒體信息檢索客戶端系統(tǒng)的設(shè)計和實現(xiàn)[D];中國科學(xué)院研究生院（計算技術(shù)研究所）;1998年

，

本文編號：2155898