【摘要】：隨著計算機技術(shù)、網(wǎng)絡(luò)技術(shù)和智能通訊技術(shù)的飛速發(fā)展,大量的圖像數(shù)據(jù)在網(wǎng)絡(luò)上廣泛傳播,并且呈現(xiàn)爆炸式增長,如何有效地管理和利用這些圖像資源已經(jīng)成為當(dāng)前面臨的一項難題。雖然人們在圖像檢索領(lǐng)域已經(jīng)取得了不少成果,但是仍然存在很多問題�；谖谋镜膱D像檢索由于效率低和人為主觀性早已無法滿足當(dāng)前大數(shù)據(jù)時代的需求;基于內(nèi)容的圖像檢索由于無法解決“語義鴻溝”問題而阻礙了其發(fā)展;基于語義的自動圖像標(biāo)注是當(dāng)前圖像檢索領(lǐng)域的主要發(fā)展方向,研究者在該領(lǐng)域做了很多研究和探索,但是仍然面臨著很多技術(shù)難題。針對圖像檢索領(lǐng)域的研究現(xiàn)狀和發(fā)展趨勢以及當(dāng)前所面臨的諸多難題,本文提出了一系列有效的改進方法,主要有以下幾點:(1)基于語義的自動圖像標(biāo)注需要利用圖像分割算法對圖像進行預(yù)處理,并且準(zhǔn)確而有效的進行圖像分割,對后面圖像特征提取以及標(biāo)注模型的構(gòu)建非常重要。本文提出了一種改進的圖像分割算法,該算法的基本思想是:首先使用Mean Shift算法對圖像進行預(yù)分割,由于Mean Shift算法對圖像邊緣比較敏感,因而可以很好的提取出圖像的邊緣信息,但是該算法也很容易產(chǎn)生很多小的區(qū)域,針對這一缺點,本文利用Ncut算法對上一步得到的圖像區(qū)域進行進一步處理,由于Ncut算法總是傾向于得到較大的圖像區(qū)域,因而可以解決Mean Shift的過分割問題,并且由于Ncut處理的是已經(jīng)分割好的圖像區(qū)域,而不是像素點,所以大大減少了計算量,提高了算法性能,然而Ncut算法也存在一定的不足,該算法是一個NP難題,進行分割之前需要首先指定分割區(qū)域個數(shù),如果該參數(shù)設(shè)置不當(dāng),也很容易產(chǎn)生過分割和欠分割現(xiàn)象,因而本文利用區(qū)域合并與分裂算法對Ncut處理后得到的分割結(jié)果進行進一步校正,對過分割區(qū)域進行合并,對欠分割區(qū)域進行分裂,盡可能提高圖像分割結(jié)果的準(zhǔn)確度。(2)本文提出了一種結(jié)合區(qū)域語義相關(guān)性和高斯混合模型的改進圖像語義標(biāo)注方法。傳統(tǒng)的高斯混合模型都是直接根據(jù)語義后驗概率的大小來得到圖像標(biāo)注結(jié)果:一種是直接選擇語義后驗概率較大的N個語義詞作為圖像的標(biāo)注結(jié)果,另一種是直接選擇語義后驗概率大于某個閾值的語義詞作為圖像標(biāo)注結(jié)果。而這種方法得到的標(biāo)注結(jié)果并不準(zhǔn)確,很容易產(chǎn)生一些多余的或者錯誤的標(biāo)注詞,影響標(biāo)注結(jié)果的準(zhǔn)確度。而且考慮到模型中的“語義鴻溝”問題,后驗概率的大小并不能完全決定其權(quán)重,僅依據(jù)后驗概率進行分類決策可能存在較大誤差。針對以上問題,本文提出了一種基于區(qū)域語義相關(guān)性的GMM圖像標(biāo)注方法,將各區(qū)域之間的語義相關(guān)性融合到GMM模型中進行綜合決策,對該模型的標(biāo)注結(jié)果進行有效的校準(zhǔn)和優(yōu)化,從而提高標(biāo)注結(jié)果的準(zhǔn)確度。
[Abstract]:With the rapid development of computer technology, network technology and intelligent communication technology, a large number of image data are widely spread on the network, and show explosive growth. How to manage and utilize these image resources effectively has become a difficult problem. Although many achievements have been made in the field of image retrieval, there are still many problems. Because of its low efficiency and artificial subjectivity, text-based image retrieval has been unable to meet the needs of the current big data era, and content-based image retrieval has hindered its development because of its inability to solve the problem of "semantic gap". Semantic automatic image annotation is the main development direction in the field of image retrieval. Researchers have done a lot of research and exploration in this field, but still face a lot of technical difficulties. In view of the present situation and development trend of image retrieval field and many difficult problems, this paper puts forward a series of effective improvement methods. The main points are as follows: (1) automatic image tagging based on semantics needs to use image segmentation algorithm to preprocess the image and to segment the image accurately and effectively. It is very important for the feature extraction and the construction of the tagging model. In this paper, an improved image segmentation algorithm is proposed. The basic idea of the algorithm is: firstly, the Mean Shift algorithm is used to pre-segment the image, because the Mean Shift algorithm is sensitive to the edge of the image. Therefore, the edge information of the image can be extracted very well, but the algorithm can easily produce a lot of small regions. In view of this shortcoming, this paper uses Ncut algorithm to further process the image region obtained from the previous step. Because the Ncut algorithm always tends to get large image regions, it can solve the problem of over-segmentation of Mean Shift, and because Ncut deals with image regions that have been segmented rather than pixels, it greatly reduces the amount of computation. The performance of the algorithm is improved, but the Ncut algorithm also has some shortcomings. This algorithm is a difficult problem of NP. It is necessary to specify the number of segmentation regions before segmentation. If the parameter is not set properly, it is easy to produce over-segmentation and under-segmentation. In this paper, we use the region merging and splitting algorithm to further correct the segmentation results obtained by Ncut processing, merge the over-segmented regions and split the under-segmented regions. The accuracy of image segmentation is improved as much as possible. (2) an improved image semantic annotation method combining regional semantic correlation with Gao Si mixed model is proposed. The traditional Gao Si mixed model is based on the size of the semantic posteriori probability directly to get the image tagging results: one is the direct selection of semantic posteriori probability of N semantic words as the image tagging results. The other is to directly select semantic words whose semantic posteriori probability is greater than a threshold value as the result of image tagging. However, the results obtained by this method are not accurate, and it is easy to produce some redundant or incorrect tagging words, which affects the accuracy of the labeling results. Considering the "semantic gap" problem in the model, the magnitude of the posterior probability can not completely determine its weight, and there may be large errors in the classification decision only based on the posterior probability. Aiming at the above problems, this paper proposes a method of GMM image tagging based on regional semantic correlation, which integrates the semantic correlation of each region into the GMM model to make comprehensive decision. The labeling results of the model are calibrated and optimized effectively, so as to improve the accuracy of the labeling results.
【學(xué)位授予單位】：華中師范大學(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 李果;;一種基于遺傳算法的Normalized Cut準(zhǔn)則圖像分割方法[J];齊齊哈爾大學(xué)學(xué)報(自然科學(xué)版);2016年03期

2 崔兆華;孫穗;陳思國;高立群;;Mean shift模糊C均值聚類圖像分割算法[J];控制與決策;2014年06期

3 李宏益;吳素萍;;Mean Shift圖像分割算法的并行化[J];中國圖象圖形學(xué)報;2013年12期

4 魏津瑜;施鶴南;蘇思沁;;基于改進算法的自動種子區(qū)域生長圖像分割[J];中南大學(xué)學(xué)報(自然科學(xué)版);2013年S2期

5 郭玉堂;韓昌剛;;基于CCA子空間和GMM的自動圖像標(biāo)注[J];計算機工程;2013年06期

6 楊棟;周秀玲;郭平;;基于貝葉斯通用背景模型的圖像標(biāo)注[J];自動化學(xué)報;2013年10期

7 張桂梅;周明明;馬珂;;基于彩色模型的重構(gòu)標(biāo)記分水嶺分割算法[J];中國圖象圖形學(xué)報;2012年05期

8 吳一全;張金礦;;二維直方圖θ-劃分最大平均離差閾值分割算法[J];自動化學(xué)報;2010年05期

9 許新征;丁世飛;史忠植;賈偉寬;;圖像分割的新理論和新方法[J];電子學(xué)報;2010年S1期

10 廖建勇;郭斯羽;黃梓效;;基于Mean Shift聚類的最大熵圖像分割方法[J];計算機仿真;2009年09期

相關(guān)碩士學(xué)位論文 前1條

1 劉苗苗;幾何活動輪廓模型在圖像分割中的應(yīng)用研究[D];南京航空航天大學(xué);2007年

，

本文編號：2337100