發(fā)布時(shí)間：2018-03-04 18:49

  本文選題：圖像檢索　切入點(diǎn)：群體優(yōu)化算法　出處：《江南大學(xué)》2017年碩士論文　論文類型：學(xué)位論文

【摘要】：隨著科學(xué)技術(shù)的進(jìn)步和互聯(lián)網(wǎng)時(shí)代的發(fā)展,以及大數(shù)據(jù)時(shí)代的到來(lái),尤其是多媒體技術(shù)和數(shù)字圖像處理技術(shù)的廣泛應(yīng)用,導(dǎo)致圖像的數(shù)據(jù)量出現(xiàn)井噴式的增長(zhǎng)。與傳統(tǒng)的文字、數(shù)字等文本的信息表達(dá)方式不同,圖像蘊(yùn)含的信息更加豐富和復(fù)雜多變,因而針對(duì)圖片的檢索和數(shù)據(jù)挖掘也更加困難。目前,如何從海量的圖像數(shù)據(jù)庫(kù)中精準(zhǔn)的檢索出期望的圖像已經(jīng)成為近十幾年來(lái)計(jì)算機(jī)科學(xué)領(lǐng)域的研究熱點(diǎn)。實(shí)現(xiàn)精確地圖像檢索的關(guān)鍵是圖像信息標(biāo)記方式的選擇,近年來(lái),利用圖像的顏色、紋理、形狀等內(nèi)容特征來(lái)標(biāo)記圖像信息的圖像檢索技術(shù),即基于內(nèi)容的圖像檢索技術(shù)(Content Based Image Retrieval,CBIR),已經(jīng)成為目前圖像檢索領(lǐng)域的主流發(fā)展方向�；趦�(nèi)容的圖像檢索具有廣泛的應(yīng)用前景和深遠(yuǎn)的研究?jī)r(jià)值和商業(yè)價(jià)值,因而該研究領(lǐng)域引起了相關(guān)研究機(jī)構(gòu)和研究人員的高度關(guān)注。目前,基于內(nèi)容的圖像檢索技術(shù)的研究雖然取得了不俗的成果,部分成果甚至已經(jīng)得到廣泛應(yīng)用,但是還有很多方面存在不足,需要進(jìn)一步的改善和優(yōu)化。傳統(tǒng)的基于內(nèi)容的圖像檢索技術(shù)采用單一的圖像視覺(jué)特征和相似性度量算法進(jìn)行圖像檢索,因而無(wú)論檢索的準(zhǔn)度和準(zhǔn)度都普遍偏低。針對(duì)該問(wèn)題,本文提出并實(shí)現(xiàn)了采用顏色和紋理兩種視覺(jué)特征以及12種相似性度量算法的基于內(nèi)容的圖像檢索方法,并采用QPSO粒子群優(yōu)化算法進(jìn)行檢索。同時(shí),通過(guò)與PSO、CLPSO、SLPSO三種粒子群優(yōu)化算法的檢索效果進(jìn)行對(duì)比選出最優(yōu)算法,并對(duì)最優(yōu)算法利用GPU加速技術(shù),從而提高圖像檢索的性能。本文使用的關(guān)鍵技術(shù)和理論方法主要包括以下四個(gè)方面:(1)由于圖像的顏色特征和紋理特征是表達(dá)圖像內(nèi)容的最直接的兩種視覺(jué)特征,因此本文綜合使用這兩種特征實(shí)現(xiàn)基于內(nèi)容的圖像檢索。顏色特征方面,基于人類視覺(jué)特征采用RGB、HSV、Lab與Gray四種顏色空間,提取圖像的顏色直方圖與顏色矩特征,并將這些特征進(jìn)行量化;紋理特征方面,采用該特征描述的兩種主要方法,灰度共生矩陣與Gabor圖像處理方法以提取圖像的紋理特征,并將紋理特征進(jìn)行量化。(2)利用12種當(dāng)前常用的相似度距離算法對(duì)目標(biāo)圖像和待檢索圖像庫(kù)中每一幅圖像提取的顏色特征和紋理特征進(jìn)行度量。(3)通過(guò)使用PSO、QPSO、CLPSO、SLPSO四種群體優(yōu)化算法獲得優(yōu)化特征、相似性度量函數(shù)以及權(quán)重之間的近似最佳組合,從而使檢索效果更加準(zhǔn)確和高效。(4)對(duì)四種群體優(yōu)化算法中最優(yōu)的QPSO算法使用C++AMP技術(shù)實(shí)現(xiàn)系統(tǒng)的GPU加速,并通過(guò)測(cè)試對(duì)加速的效果進(jìn)行驗(yàn)證。
[Abstract]:Along with the progress and development of the Internet era of science and technology, and the arrival of the era of big data, especially the wide application of multimedia technology and digital image processing technology, image data lead to blowout growth. With the traditional text information expression of digital text of the different image contains more abundant information and complex and so for the image retrieval and data mining is more difficult. At present, how from the huge image database retrieval in accurate expectations image has become in recent years the computer science research led domain. To realize accurate image retrieval is the key to image information marking way, in recent years, the use of image the color, texture, image retrieval technology to mark the shape of image information content characteristic, namely the content-based image retrieval technology (Content Based Image Retri Eval, CBIR), has become the mainstream of the development direction of the field of image retrieval at present. It has wide application prospect and great research value and commercial value of content based image retrieval, and the research field and attracted the attention of the relevant research institutions and researchers. At present, research on the image retrieval technique has achieved good results based on some results and even has been widely used, but there are still many deficiencies and need further improvement and optimization. Based on the technology used in single image feature and similarity measure algorithm for image retrieval content-based image retrieval and traditional, both accuracy and the accuracy of the retrieval are generally low for. This problem, this paper proposes and implements the two kinds of color and texture feature of visual and 12 similar image retrieval based on content measurement algorithm Using QPSO method, and the particle swarm optimization algorithm for retrieval. At the same time, with PSO, CLPSO, SLPSO three kinds of particle swarm optimization algorithm for retrieval results were compared to select the optimal algorithm, and accelerate technology on the optimal use of GPU algorithm, so as to improve the performance of image retrieval. In this paper, the key technology and theory method mainly includes the following four aspects: (1) the color features and texture features of the image are two kinds of visual features of the most direct expression of the image content, so the use of the two kinds of features for content-based image retrieval. Color characteristics of human visual features using RGB, based on HSV, Lab and Gray four kinds of color space the extraction of image, color histogram and color moment features, and quantified feature; texture feature, the two main methods of the description of the features of the gray level co-occurrence matrix and Gabor image processing. By the method of extracting image texture features, and quantify the texture features. (2) using the 12 kinds of similarity distance algorithm commonly used to retrieve the target image and each image to extract the color and texture features of the image library to measure. (3) by using PSO, QPSO, CLPSO, SLPSO four the group optimization algorithm to obtain optimal feature, similarity measure between the function and the weights of the approximate optimal combination, so as to make the retrieval results more accurate and efficient. (4) the use of C++AMP technology to realize the system GPU acceleration of four group optimization algorithm the optimal QPSO algorithm, and through the test of the effect of acceleration is verified.

【學(xué)位授予單位】：江南大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類號(hào)】：TP391.41;TP18

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 陳風(fēng);田雨波;楊敏;;基于CUDA的并行粒子群優(yōu)化算法研究及實(shí)現(xiàn)[J];計(jì)算機(jī)科學(xué);2014年09期

2 張小軍;任帥;;計(jì)算機(jī)神經(jīng)網(wǎng)絡(luò)中粒子群優(yōu)化算法的應(yīng)用[J];計(jì)算機(jī)光盤(pán)軟件與應(yīng)用;2014年08期

3 王澤寰;王鵬;;GPU并行計(jì)算編程技術(shù)介紹[J];科研信息化技術(shù)與應(yīng)用;2013年01期

4 楊柳;劉鐵英;;GPU架構(gòu)下的并行計(jì)算[J];吉林大學(xué)學(xué)報(bào)(信息科學(xué)版);2012年06期

5 詹洪陳;袁杰;;圖像處理的GPU加速技術(shù)研究[J];現(xiàn)代電子技術(shù);2012年20期

6 厲旭杰;;GPU加速的圖像匹配技術(shù)[J];計(jì)算機(jī)工程與應(yīng)用;2012年02期

7 唐朝霞;章慧;徐冬梅;;一種改進(jìn)的粒子群算法和相關(guān)反饋的圖像檢索[J];計(jì)算機(jī)科學(xué);2011年10期

8 李太勇;吳江;朱波;方冰;;一種基于距離度量的自適應(yīng)粒子群優(yōu)化算法[J];計(jì)算機(jī)科學(xué);2010年10期

9 許相莉;張利彪;劉向東;于哲舟;周春光;;基于粒子群的圖像檢索相關(guān)反饋算法[J];電子學(xué)報(bào);2010年08期

10 潘昊;鄭明;;免疫粒子群算法在神經(jīng)網(wǎng)絡(luò)訓(xùn)練中的應(yīng)用[J];計(jì)算機(jī)工程與應(yīng)用;2009年34期

，

本文編號(hào)：1566875