數(shù)字圖像隱寫(xiě)分析研究
發(fā)布時(shí)間：2018-01-08 20:25
本文關(guān)鍵詞：數(shù)字圖像隱寫(xiě)分析研究 出處：《上海大學(xué)》2016年博士論文 論文類(lèi)型：學(xué)位論文
更多相關(guān)文章： 信息隱藏 數(shù)字圖像 隱寫(xiě) 隱寫(xiě)分析 重分布?xì)埐?/b> 殘差對(duì)比度 多分辨率分解 多樣化集成
【摘要】：數(shù)字圖像隱寫(xiě)和隱寫(xiě)分析技術(shù)是兩個(gè)對(duì)立的學(xué)科。隱寫(xiě)技術(shù)主要利用多媒體數(shù)據(jù)實(shí)現(xiàn)信息的秘密傳遞,即隱蔽通信。隱寫(xiě)分析是發(fā)現(xiàn)隱寫(xiě)行為的技術(shù)。本文以隱寫(xiě)分析技術(shù)為研究目標(biāo),結(jié)合內(nèi)容自適應(yīng)隱寫(xiě)方法,提出了多種有效的隱寫(xiě)分析方法。同時(shí),為了提高分類(lèi)器的檢測(cè)能力,結(jié)合集成學(xué)習(xí)理論,提出了多樣化集成分類(lèi)器。取得的成果如下:1.基于重分布?xì)埐畹牡途S空域圖像隱寫(xiě)分析提出了2929維重分布?xì)埐羁沼驁D像隱寫(xiě)分析特征。該特征由兩類(lèi)子特征構(gòu)成,第一類(lèi)子特征是殘差的一階直方圖。該部分特征由較大閾值門(mén)限生成,能夠捕捉分布在邊緣以及紋理區(qū)域的隱寫(xiě)改變。第二類(lèi)子特征是重分布?xì)埐畹囊浑A直方圖。該部分特征利用平移參數(shù)和殘差的反相關(guān)性生成,重分布機(jī)制能夠增加特征的多樣性,提高特征的檢測(cè)準(zhǔn)確率。為了檢測(cè)特征的有效性,我們選用內(nèi)容自適應(yīng)安全隱寫(xiě)算法進(jìn)行測(cè)試。實(shí)驗(yàn)結(jié)果顯示,在低嵌入率下,同已有的隱寫(xiě)分析方法相比,重分布特征對(duì)于內(nèi)容自適應(yīng)隱寫(xiě)算法的檢測(cè)錯(cuò)誤率降低了5.65%。2.基于紋理復(fù)雜度和殘差對(duì)比度的低維空域圖像隱寫(xiě)分析提出了基于紋理復(fù)雜度和殘差對(duì)比度的2363維空域圖像隱寫(xiě)分析算法。根據(jù)內(nèi)容自適應(yīng)隱寫(xiě)算法原理,秘密信息被嵌入到圖像的紋理以及邊緣區(qū)域,而圖像的平滑區(qū)域不會(huì)嵌入秘密信息。因此,為了能夠根據(jù)圖像的紋理進(jìn)行針對(duì)性特征提取,定義了波動(dòng)函數(shù)評(píng)價(jià)圖像的紋理復(fù)雜度,然后根據(jù)波動(dòng)函數(shù)提取出圖像中最復(fù)雜的區(qū)域(子圖像)。對(duì)于提取的子圖像和原始圖像,算法使用線(xiàn)性及非線(xiàn)性濾波器獲得多樣化殘差,然后將不同殘差的比值轉(zhuǎn)換成角度。同時(shí),將殘差的l2范數(shù)作為角度的對(duì)應(yīng)權(quán)值,最終將加權(quán)的角度直方圖作為殘差對(duì)比度特征。該特征不僅可以有效的表達(dá)不同殘差之間的聯(lián)合統(tǒng)計(jì)分布,而且特征維數(shù)隨著閾值門(mén)限值呈線(xiàn)性變化。同已有的空域圖像隱寫(xiě)分析算法相比,在較低的嵌入率下,提出的隱寫(xiě)分析算法使用低維特征可以實(shí)現(xiàn)較高的檢測(cè)準(zhǔn)確率。3.基于多分辨率分解和仿射變換的JPEG圖像隱寫(xiě)分析提出了基于多分辨率分解和仿射變換的高維JPEG圖像隱寫(xiě)分析算法。我們認(rèn)為JPEG圖像是由若干不同分辨率的子圖像以非線(xiàn)性方式構(gòu)成。因此,如果可以將原始JPEG圖像進(jìn)行多分辨率分解,那么隱寫(xiě)改變會(huì)以非線(xiàn)性方式分布于不同的JPEG子圖像中。同時(shí),通過(guò)逐步剝離圖像的平滑區(qū)域,可以更好的凸顯出隱寫(xiě)改變,從而增加特征的檢測(cè)準(zhǔn)確率。為了獲得多分辨率的JPEG圖像,首先將JPEG圖像解壓縮成空域圖像,在空域中利用多分辨算法進(jìn)行分解。然后將不同分辨率的空域子圖像重新壓縮,獲得多幅JPEG圖像。其次將每個(gè)DCT(離散余弦變換)系數(shù)看成是獨(dú)立的平面,按照不同方向獲取殘差平面。將兩個(gè)殘差系數(shù)間的比值轉(zhuǎn)換成角度,同時(shí)將DCT系數(shù)的l2范數(shù)作為角度的權(quán)重,最終把角度和權(quán)值的聯(lián)合作為提取的特征。為了增加特征的多樣性,我們使用仿射變換對(duì)轉(zhuǎn)換的角度進(jìn)行旋轉(zhuǎn),從而獲得新的特征。相比已有JPEG圖像隱寫(xiě)分析算法,在不同嵌入率下,提出的隱寫(xiě)分析算法能夠提高特征的檢測(cè)準(zhǔn)確率。4.多樣化集成分類(lèi)器提出了多樣化集成分類(lèi)器算法。集成分類(lèi)器能夠解決高維特征的訓(xùn)練與分類(lèi),但是在原始分類(lèi)器中仍然存在兩個(gè)不足。第一個(gè)不足是最終分類(lèi)器的選擇策略。面對(duì)眾多訓(xùn)練好的基分類(lèi)器,原始的算法會(huì)丟棄絕大多數(shù)的基分類(lèi)器,只選擇具有最小訓(xùn)練誤差的基分類(lèi)器作為最終分類(lèi)器。為了防止過(guò)擬合現(xiàn)象發(fā)生,增強(qiáng)最終分類(lèi)器的泛化能力,我們對(duì)全部基分類(lèi)器使用Bagging集成策略,生成最終分類(lèi)器。該算法能夠充分利用被丟棄的基分類(lèi)器,從而增強(qiáng)其泛化能力,避免過(guò)擬合現(xiàn)象。第二個(gè)不足是子分類(lèi)器的弱分類(lèi)能力會(huì)影響最終分類(lèi)器的檢測(cè)性能。為了提升子分類(lèi)器的分類(lèi)性能,我們采用Adaboost集成學(xué)習(xí)策略提升單一子分類(lèi)器的分類(lèi)能力,最終提升分類(lèi)器的整體檢測(cè)能力。對(duì)于多種隱寫(xiě)分析特征的檢測(cè)結(jié)果顯示,利用多樣化集成分類(lèi)器可以提高特征的檢測(cè)準(zhǔn)確率。本文以隱寫(xiě)分析技術(shù)為目標(biāo),從重分布?xì)埐顦?gòu)造、紋理復(fù)雜度和殘差對(duì)比度特征提取、多分辨率分解和多樣化集成分類(lèi)器設(shè)計(jì)等角度對(duì)隱寫(xiě)分析技術(shù)進(jìn)行了分析與研究。
[Abstract]:Digital image steganography and steganalysis are two opposite subjects. Steganography mainly use multimedia data to realize the information transmission of secret covert communication. Namely, steganalysis is found in steganography technology. Based on the behavior of steganalysis technique as the research object, combined with the content of adaptive steganography method is proposed a variety of effective steganalysis methods. At the same time, in order to improve the detection capability of classifier, integrated learning theory, put forward the diversified integrated classifier. The results are as follows: 1. based on the low dimensional spatial domain image hidden redistribution residual analysis proposed 2929 dimensional spatial redistribution of residual image steganalysis features. The characteristics of composed of two kinds of features, the first sub feature is a first-order histogram. The residual part features generated by the larger the threshold, to capture changes in the distribution of write edges and texture regions. Second kinds of hidden Feature is the first-order histogram redistribution of residual. This part features using the translation parameters and residual anti correlation generation, redistribution mechanism can increase the diversity characteristics, improve the feature detection accuracy. In order to check the validity of the feature, we use content adaptive security steganographic algorithm is tested. Experimental results show that in low the embedding rate, with the existing steganalysis method compared to heavy distribution for the detection of the error of adaptive steganography algorithm based on 5.65%.2. to reduce the rate of low dimensional spatial images texture complexity and residual contrast analysis proposed 2363 dimensional spatial domain image texture complexity and implicit residual contrast analysis algorithm based on according to the content of adaptive steganography algorithm principle, the secret information is embedded into the image texture and edge region, and the secret information of the image smoothing area not embedded. Therefore, for It can be targeted according to the image texture feature extraction, texture image definition evaluation function fluctuation complexity, then according to the wave function to extract the most complex regions in the image (sub images). The extracted sub image and the original image. The algorithm uses a linear and nonlinear filter to obtain diverse residuals, then different residuals the ratio of conversion into perspective. At the same time, the L2 norm residuals as corresponding weight angle, will eventually be weighted angle histogram as residual contrast features. This feature not only can be expressed efficiently between different residual joint statistical distribution, and the threshold value dimension with linearly implicit spatial image with the existing writing the analysis algorithm, at low embedding rate, the proposed steganalysis algorithm using low dimensional feature can achieve higher detection accuracy of.3. based on multi resolution JPEG images decomposition rate and affine transform writing analysis put forward high dimensional JPEG image hidden multi-resolution decomposition and affine transform analysis based algorithm. We believe that the JPEG image is composed of a plurality of different resolution sub image in a nonlinear way. Therefore, if the original JPEG image multi-resolution decomposition, then steganography change be in a nonlinear way distributed in different JPEG sub image. At the same time, the smooth region gradually stripped of the image, you can better highlight the steganography change, thereby increasing the accuracy of the feature detection. In order to obtain the JPEG image resolution, the JPEG image decompression into spatial domain image, using multiresolution decomposition algorithm in the spatial domain. Then different spatial resolution image compression subsystem, to obtain JPEG images. Then each DCT (discrete cosine transform) coefficients as independent The plane, according to the different direction. The plane gets residual ratio of two residual coefficient of conversion between angle, while the L2 norm DCT coefficients as angle weights, finally put joint angle and weight as the extracted features. In order to increase the diversity characteristics, we use affine transform to convert rotation angle in order to obtain new features. Compared with the existing JPEG image steganalysis algorithm in different embedding rate, the proposed steganalysis algorithm can improve the detection accuracy of.4. features of diverse ensemble classifier proposed diverse ensemble classification algorithm for training and classification. The ensemble classifier can solve high dimensional features, but still in the original classifier there are two problems. The first problem is the final classifier selection strategy. In the face of many base classifiers trained, the original algorithm will discard most of the base class Is only the base classifier with minimum training error of the final classifier. In order to prevent overfitting phenomenon, finally enhance the generalization ability of the classifier, we have all the base classifiers using Bagging integration strategy, generate the final classifier. This algorithm can make full use of the base classifier is discarded, so as to enhance its generalization ability, avoid the overfitting phenomenon second is the lack of detection performance of weak classification ability of classifier will affect the final classifier. In order to improve the classification performance of classifier, we use the classification ability of Adaboost integrated learning strategy to improve single classifier, improve the overall detection ability of the classifier. The final results for the detection of a variety of steganalysis features, using diverse ensemble classifier can improve the feature detection accuracy. Based on the steganalysis technology as the goal, from the distribution of residual. The steganalysis technology is analyzed and researched based on texture complexity and residual contrast feature extraction, multi-resolution decomposition and diversified ensemble classifier design.
【學(xué)位授予單位】：上海大學(xué)
【學(xué)位級(jí)別】：博士
【學(xué)位授予年份】：2016
【分類(lèi)號(hào)】：TP391.41;TP309
【相似文獻(xiàn)】
相關(guān)期刊論文 前10條
1 陳鵬;王衍波;端木慶峰;劉宇鋒;徐敏;;互聯(lián)網(wǎng)隱寫(xiě)分析系統(tǒng)的研究與設(shè)計(jì)[J];網(wǎng)絡(luò)安全技術(shù)與應(yīng)用;2008年01期
2 孫子文;李慧;;基于偏最小二乘回歸建模的量化隱寫(xiě)分析[J];系統(tǒng)仿真學(xué)報(bào);2013年04期
3 劉鴻霞;夏春和;;圖像隱寫(xiě)分析現(xiàn)狀研究[J];計(jì)算機(jī)工程與設(shè)計(jì);2006年01期
4 黃聰;宣國(guó)榮;高建炯;施云慶;;基于模式識(shí)別的多類(lèi)隱寫(xiě)分析[J];計(jì)算機(jī)工程與應(yīng)用;2006年27期
5 鈕心忻;楊義先;;信息隱寫(xiě)與隱寫(xiě)分析研究框架探討[J];電子學(xué)報(bào);2006年S1期
6 何平;周輝;常向鋒;;隱寫(xiě)分析技術(shù)研究[J];裝備制造技術(shù);2007年07期
7 于y，
本文編號(hào)：1398559
本文鏈接：http://www.sikaile.net/shoufeilunwen/xxkjbs/1398559.html
最近更新
教材專(zhuān)著
