本文選題：遙感圖像 + 全參考�。� 參考：《西安科技大學(xué)》2017年碩士論文

【摘要】：目前已經(jīng)涌現(xiàn)了大量的圖像質(zhì)量評價算法且在評價普通圖像時能夠取得較好的效果。遙感圖像作為一種高空拍攝的高分辨率自然圖像,與普通的自然圖像存在很多區(qū)別,采用現(xiàn)有的圖像質(zhì)量評價方法不能達(dá)到要求。因此就需要結(jié)合遙感圖像本身的特點研究出更符合人眼視覺的質(zhì)量評價方法。本文深入分析了結(jié)構(gòu)相似性理論(Structural Similarity,SSIM),針對遙感圖像邊緣多尺度、紋理錯綜復(fù)雜的特點,結(jié)合人眼視覺系統(tǒng),從全參考和無參考兩個方面對SSIM方法進(jìn)行改進(jìn)。人眼對邊緣區(qū)域及其兩側(cè)的對比度更加敏感,紋理區(qū)域本身包含整幅圖像的大部分結(jié)構(gòu)信息,然而SSIM將所有像素一視同仁,不符合人眼視覺系統(tǒng)。因此,本文給出了一種了全參考的基于邊緣紋理區(qū)域質(zhì)量評價算法(ET_SSIM)。該方法采用非下采樣輪廓波變換進(jìn)行多尺度分解,將子圖像進(jìn)行k-means邊緣檢測及細(xì)化融合,最終得到邊緣區(qū)域。對圖像計算其梯度幅值,設(shè)置兩個閾值,將滿足區(qū)間的像素提取出來得到紋理區(qū)域。然后,使用邊緣計算對比度分量,紋理計算結(jié)構(gòu)相似度分量,對SSIM進(jìn)行改進(jìn)。由于遙感圖像缺少主觀評價數(shù)據(jù)庫,為了更好的檢驗本文方法的準(zhǔn)確性,建立了遙感圖像數(shù)據(jù)庫進(jìn)行驗證。實驗表明,本文的全參考方法ET_SSIM比MSE、PSNR、SSIM及GSSIM的線性相關(guān)度分別提高了 22.8%,6.7%,1.3%,0.7%。為了得到一種更加通用的無參考遙感圖像評價方法,本文對ET_SSIM進(jìn)行改進(jìn)。采用“再降質(zhì)”的方式構(gòu)造出參考圖像,將邊緣紋理區(qū)域與平滑區(qū)域分開評價,ET_SSIM對邊緣紋理區(qū)域評價,SSIM對平滑區(qū)域評價,根據(jù)人眼對邊緣紋理及平滑區(qū)域的不同重視程度加權(quán)求和,得到最終結(jié)果。最后,在相同SSIM值不同主觀感受的遙感圖像集、自建數(shù)據(jù)庫和LIVE數(shù)據(jù)庫的實驗說明本文方法VSSIM評價的單調(diào)性和一致性略低于ET_SSIM,但是作為一種無參考方法,其準(zhǔn)確性明顯好于SSIM。且本文的無參考方法VSSIM方法比目前主流的無參考方法BLIINDS-II線性相關(guān)度提高了 1.3%。
[Abstract]:At present, a large number of image quality evaluation algorithms have emerged and can achieve good results in the evaluation of ordinary images. As a kind of high-resolution natural image, remote sensing image is different from ordinary natural image, and the existing image quality evaluation method can not meet the requirements. Therefore, it is necessary to combine the characteristics of remote sensing images to develop a quality evaluation method that is more suitable for human vision. In this paper, the structural similarity theory is deeply analyzed. Aiming at the multi-scale and intricate texture of remote sensing image, the SSIM method is improved from two aspects: full reference and no reference. The human eye is more sensitive to the contrast of the edge region and its two sides, and the texture region itself contains most of the structural information of the whole image. However, SSIM treats all pixels equally and does not conform to the human visual system. Therefore, an all-reference quality evaluation algorithm based on edge texture region is presented. In this method, the non-downsampling contour wave transform is used for multi-scale decomposition, and the k-means edge detection and thinning fusion are performed on the sub-image, and the edge region is finally obtained. The gradient amplitude of the image is calculated and two thresholds are set to extract the pixels satisfying the range to obtain the texture region. Then, the contrast component is computed by edge and the structural similarity component is calculated by texture, and the SSIM is improved. Because remote sensing image lacks subjective evaluation database, in order to verify the accuracy of this method, a remote sensing image database is established for verification. The experimental results show that the linear correlation of the full reference method ET_SSIM is 22.86.7and 1.30.70% higher than that of MSE PSNRIM and GSSIM, respectively. In order to obtain a more general evaluation method of remote sensing images without reference, this paper improves ET_SSIM. The reference image is constructed by "redegrade" method, and the edge texture area is evaluated separately from the smooth area by ETS IM and the smooth area is evaluated by SSIM. The final results are obtained by weighted summation according to the different emphasis on edge texture and smooth region. Finally, in the remote sensing image set with the same SSIM value and different subjective feelings, the experiments of self-built database and LIVE database show that the monotonicity and consistency of VSSIM evaluation in this paper is slightly lower than that of ETSSS, but as a non-reference method, its accuracy is obviously better than that of SSIM. The linear correlation of the non-reference method VSSIM method is 1.3% higher than that of the current mainstream non-reference method BLIINDS-II method.
【學(xué)位授予單位】：西安科技大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2017
【分類號】：TP751

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 朱睿;李朝鋒;;一種改進(jìn)的卷積神經(jīng)網(wǎng)絡(luò)的無參考JPEG2000圖像質(zhì)量評價方法[J];計算機應(yīng)用與軟件;2017年01期

2 賈迪;董娜;孟祥福;李思慧;陳碩;;一種圖像的連續(xù)性邊緣提取方法[J];計算機工程與科學(xué);2015年02期

3 李俊峰;張飛燕;戴文戰(zhàn);潘海鵬;;基于圖像相關(guān)性和結(jié)構(gòu)信息的無參考圖像質(zhì)量評價[J];光電子·激光;2014年12期

4 賈惠珍;孫權(quán)森;王同罕;;結(jié)合感知特征和自然場景統(tǒng)計的無參考圖像質(zhì)量評價[J];中國圖象圖形學(xué)報;2014年06期

5 謝秀華;李陶深;;一種基于改進(jìn)PSO的K-means優(yōu)化聚類算法[J];計算機技術(shù)與發(fā)展;2014年02期

6 穆為磊;高建民;王昭;姜洪權(quán);陳富民;黨長營;;考慮人眼視覺特性的射線檢測數(shù)字圖像質(zhì)量評價方法[J];西安交通大學(xué)學(xué)報;2013年07期

7 邵宇;孫富春;李洪波;;基于視覺特性的無參考型遙感圖像質(zhì)量評價方法[J];清華大學(xué)學(xué)報(自然科學(xué)版);2013年04期

8 孔繁鏘;;結(jié)合HVS和相似性度量的圖像質(zhì)量評價測度[J];中國圖象圖形學(xué)報;2011年07期

9 孫玉寶;費選;韋志輝;肖亮;胡晰遠(yuǎn);呂戰(zhàn)強;;基于Contourlet的圖像感知質(zhì)量評價[J];電子學(xué)報;2011年03期

10 白宏剛;王曉蕊;;紅外遙感器設(shè)計參數(shù)與NIIRS的定量關(guān)系研究[J];電子科技;2010年04期

相關(guān)博士學(xué)位論文 前4條

1 劉德磊;基于分形分析的圖像質(zhì)量評價[D];華南理工大學(xué);2014年

2 馬旭東;光學(xué)遙感影像壓縮及融合的質(zhì)量評價研究[D];武漢大學(xué);2014年

3 顧營迎;航天光學(xué)遙感器圖像終端像質(zhì)評價方法研究[D];中國科學(xué)院研究生院（長春光學(xué)精密機械與物理研究所）;2013年

4 修吉宏;基于圖像功率譜的航空圖像質(zhì)量判別技術(shù)研究[D];中國科學(xué)院研究生院（長春光學(xué)精密機械與物理研究所）;2005年

相關(guān)碩士學(xué)位論文 前4條

1 薛萬勛;基于邊緣特征的遙感圖像質(zhì)量評價方法研究[D];中國科學(xué)院國家空間科學(xué)中心;2016年

2 王旭;無參考遙感圖像質(zhì)量綜合評價算法研究[D];西安電子科技大學(xué);2015年

3 鄧勤;衛(wèi)星顫振對遙感成像質(zhì)量影響研究及實驗驗證[D];浙江大學(xué);2013年

4 徐云生;基于Contourlet變換的圖像質(zhì)量評價方法研究[D];中國科學(xué)技術(shù)大學(xué);2010年

，

本文編號：1925914