本文關(guān)鍵詞：基于PRNU的自然圖像和計(jì)算機(jī)生成圖像來源取證　出處：《湖南大學(xué)》2012年碩士論文　論文類型：學(xué)位論文

  更多相關(guān)文章： 圖像來源鑒別 計(jì)算機(jī)生成圖像 PRNU 分形維數(shù) CFA插值

【摘要】：隨著數(shù)碼設(shè)備和圖像處理軟件技術(shù)的快速發(fā)展,人們已可以很輕松地獲取和修改數(shù)字圖像。但先進(jìn)的技術(shù)在給人們的生活帶來便利的同時(shí),也暴露出了很多安全問題。若不法分子將偽造的數(shù)字圖像用于新聞、證物和科學(xué)研究等正式場合,將會混淆視聽,對事件的真實(shí)性和社會的穩(wěn)定性產(chǎn)生嚴(yán)重的影響。因此,確保數(shù)字圖像真實(shí)性和完整性的數(shù)字圖像取證技術(shù)已受到廣大研究者的關(guān)注。 本文主要研究了自然圖像和計(jì)算機(jī)生成圖像的來源鑒別。首先,對數(shù)字圖像取證技術(shù)的研究背景、意義及國內(nèi)外研究現(xiàn)狀進(jìn)行了闡述,對數(shù)字圖像取證技術(shù)的研究內(nèi)容及研究成果進(jìn)行了綜述。其次,對本文算法所涉及的相關(guān)理論知識進(jìn)行了介紹。最后,針對自然圖像和計(jì)算機(jī)生成圖像來源的識別問題,提出了兩種鑒別算法： 1.提出了一種基于復(fù)合特征的兩類圖像來源鑒別方法。該方法基于自然圖像和計(jì)算機(jī)生成圖像在統(tǒng)計(jì)、紋理和噪聲特性上的不同,首先提取灰度圖像直方圖在空域和小波域的均值、方差、峰值、偏度和中位數(shù)作為統(tǒng)計(jì)特征；然后提取灰度圖像及其小波域子帶的分形維數(shù)作為紋理特征；最后針對基于小波濾波提取的光照響應(yīng)不一致性噪聲(Photo-Response Non-Uniformity Noise, PRNU)的不足,先將圖像經(jīng)過高斯高通濾波預(yù)處理,再提取PRNU的統(tǒng)計(jì)和紋理特征,作為噪聲特征,共48維特征。采用支持向量機(jī)(Support Vector Machine, SVM)進(jìn)行分類,平均鑒別率為94.29%,其中對計(jì)算機(jī)生成圖像鑒別率為97.30%,自然圖像鑒別率為91.28%,表明該方法適合兩類圖像的來源鑒別,而且鑒別效果比已有方法在性能上有所改善。 2.提出了一種基于PRNU與彩色濾鏡陣列(Color Filter Array, CFA)插值特性的兩類圖像來源鑒別方法。該方法利用CFA插值是自然圖像的特有操作和PRNU作為相機(jī)的“數(shù)字指紋”的特性,首先分析了CFA插值對PRNU的影響在兩類圖像中的差異,然后利用PRNU鄰域方差直方圖來表達(dá)此不同,并分別從RGB三顏色通道中提取PRNU鄰域方差累加和及其方差直方圖的最大值、加權(quán)平均和方差,共12維特征,最后采用SVM進(jìn)行分類,平均鑒別率達(dá)到96.55%,為自然圖像和計(jì)算機(jī)生成圖像的鑒別提供一種新的有效方法。 本文提出的兩個(gè)來源鑒別算法,能將自然圖像和計(jì)算機(jī)生成圖像進(jìn)行有效地準(zhǔn)確地分類。
[Abstract]:With the rapid development of digital equipment and image processing software technology, people can easily obtain and modify digital images. It also exposes a lot of security problems. If criminals use fake digital images for official occasions such as news, evidence and scientific research, it will confuse the public. It has a serious impact on the authenticity of events and the stability of society. Therefore, digital image forensics, which ensures the authenticity and integrity of digital images, has attracted the attention of many researchers. This paper mainly studies the source identification of natural images and computer-generated images. Firstly, the research background, significance and research status of digital image forensics technology are described. The research content and research results of digital image forensics technology are summarized. Secondly, the related theoretical knowledge of this algorithm is introduced. Finally. In order to identify the source of natural image and computer generated image, two identification algorithms are proposed. 1. Two kinds of image source identification methods based on compound features are proposed, which are based on the differences of statistical, texture and noise characteristics between natural images and computer-generated images. Firstly, the mean, variance, peak value, deviation and median of gray image histogram in spatial domain and wavelet domain are extracted as statistical features. Then the fractal dimension of gray image and its sub-band in wavelet domain is extracted as texture feature. Finally, the deficiency of Photo-Response Non-Uniformity Noise (PRNU) based on the inconsistent noise of illumination response extracted by wavelet filter is discussed. Firstly, the image is pre-processed by Gao Si high-pass filter, and then the statistical and texture features of PRNU are extracted as noise features. The support vector machine support Vector Machine (SVMs) was used to classify the 48 dimensional features. The average discriminant rate was 94.29%. The computer generated image identification rate is 97.30 and the natural image identification rate is 91.28, which indicates that this method is suitable for the source identification of two kinds of images. Moreover, the discrimination effect is better than that of the existing methods. 2. A color Filter Array based on PRNU and color filter array is proposed. This method uses CFA interpolation as the special operation of natural image and PRNU as the "digital fingerprint" of camera. The difference of the influence of CFA interpolation on PRNU in the two kinds of images is analyzed firstly, and then the difference is expressed by using the PRNU neighborhood variance histogram. The maximum, weighted average and variance of the PRNU neighborhood variance cumulative sum and its variance histogram were extracted from the RGB three-color channel, respectively, and the 12 dimensional features were obtained. Finally, SVM was used to classify. The average discriminant rate is 96.55, which provides a new and effective method for the identification of natural images and computer-generated images. The two source identification algorithms proposed in this paper can classify natural images and computer generated images effectively and accurately.
【學(xué)位授予單位】：湖南大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2012
【分類號】：TP391.41;D918.2

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 王波;孫璐璐;孔祥維;尤新剛;;圖像偽造中模糊操作的異常色調(diào)率取證技術(shù)[J];電子學(xué)報(bào);2006年S1期

2 周琳娜;王東明;郭云彪;楊義先;;基于數(shù)字圖像邊緣特性的形態(tài)學(xué)濾波取證技術(shù)[J];電子學(xué)報(bào);2008年06期

3 王波;孔祥維;尤新剛;付海燕;;基于協(xié)方差矩陣的CFA插值盲檢測方法[J];電子與信息學(xué)報(bào);2009年05期

4 王波;孔祥維;付海燕;;聯(lián)合OC-SVM和MC-SVM的圖像來源取證方法[J];計(jì)算機(jī)研究與發(fā)展;2009年09期

5 張亞莉,郭雷,楊諸勝;一種用于圖像認(rèn)證的半脆弱性數(shù)字水印算法[J];計(jì)算機(jī)應(yīng)用研究;2005年11期

6 孔繁庭;劉俊華;;基于邊界程度的圖像插值算法[J];計(jì)算機(jī)應(yīng)用;2011年06期

7 姚丹紅;蘇波;李生紅;;基于分形維數(shù)的計(jì)算機(jī)生成圖像檢測方法[J];通信技術(shù);2008年12期

8 譚茹;王相海;辛玲;;一類幾何紋理生成方法[J];微電子學(xué)與計(jì)算機(jī);2007年06期

9 彭瑞東,謝和平,鞠楊;二維數(shù)字圖像分形維數(shù)的計(jì)算方法[J];中國礦業(yè)大學(xué)學(xué)報(bào);2004年01期

10 宋玉杰,譚鐵牛;基于脆弱性數(shù)字水印的圖象完整性驗(yàn)證研究[J];中國圖象圖形學(xué)報(bào);2003年01期

相關(guān)碩士學(xué)位論文 前3條

1 余紹鵬;成像設(shè)備源辨識中的圖像特征提取方法研究[D];華南理工大學(xué);2011年

2 于洋;數(shù)碼照片和計(jì)算機(jī)生成圖像的圖像源鑒別[D];大連理工大學(xué);2007年

3 焦春燕;基于圖像的魯棒性數(shù)字水印技術(shù)研究[D];中國海洋大學(xué);2009年

，

本文編號：1406691