基于內(nèi)在生成機(jī)制的多尺度結(jié)構(gòu)相似性圖像質(zhì)量評(píng)價(jià)
doi: 10.11999/JEIT150616
-
2.
(中國(guó)礦業(yè)大學(xué)信息與電氣工程學(xué)院 徐州 221116) ②(中國(guó)礦業(yè)大學(xué)江蘇省煤礦電氣與自動(dòng)化工程實(shí)驗(yàn)室 徐州 221008)
基金項(xiàng)目:
江蘇省煤礦電氣與自動(dòng)化工程實(shí)驗(yàn)室建設(shè)項(xiàng)目(2014KJZX05，江蘇省產(chǎn)學(xué)研前瞻性聯(lián)合研究項(xiàng)目(BY2014028-01)，中央高校重大項(xiàng)目培育專項(xiàng)(2014ZDPY16)，國(guó)家自然科學(xué)基金(51274202)，江蘇省自然科學(xué)基金(2013-2016, BK20131124)和中央高校創(chuàng)新人才基金(2013RC11)
Multiple-scale Structural Similarity Image Quality Assessment Based on Internal Generative Mechanism
-
2.
(School of Information and Electrical Engineering, China University of Mining and Technology, Xuzhou 221116, China)
Funds:
The Jiangsu Province Laboratory of Electrical and Automation Engineering for Coal Mining (2014KJZX05), The Perspective Research Foundation of Production Study and Research Alliance of Jiangsu Province (BY2014028-01), The Fundamental Research Foundation for the Central Universities (2014ZDPY16), The National Natural Science Foundation of China (51274202), The Natural Science Foundation of Jiangsu Province (BK201311240), The Fundamental Research Funds for the Central Universities (2013RC11)
-
摘要: 該文針對(duì)多尺度結(jié)構(gòu)相似性(Multiple-scale Structural SIMilarity, MSSIM)圖像質(zhì)量評(píng)價(jià)算法對(duì)圖像信息不確定部分度量能力的不足，結(jié)合人類視覺(jué)系統(tǒng)(HVS)，提出基于內(nèi)在生成機(jī)制(internal generative mechanism)的iMSSIM算法。首先采用基于逐段式自回歸(Piecewise AutoRegressive, PAR)模型的內(nèi)在生成機(jī)制將失真圖像和原始圖像分解成采用MSSIM算法評(píng)分的圖像內(nèi)容預(yù)測(cè)部分和采用PSNR評(píng)分的圖像信息不確定部分；然后采用均方誤差(MSE)進(jìn)行加權(quán)來(lái)聯(lián)合這兩部分評(píng)分獲得最終結(jié)果。在基準(zhǔn)數(shù)據(jù)庫(kù)上完成的對(duì)比實(shí)驗(yàn)表明：該算法不僅在不同失真類型上性能最好，且在6個(gè)公開(kāi)數(shù)據(jù)庫(kù)上的性能優(yōu)于現(xiàn)有算法。
-
關(guān)鍵詞:
- 圖像質(zhì)量評(píng)價(jià) /
- 多尺度結(jié)構(gòu)相似性 /
- 內(nèi)在生成機(jī)制 /
- 逐段式自回歸模型
Abstract: In order to improve image information uncertainty measurement of the Multiple-scale Structural SIMilarity (MSSIM), a novel algorithm called iMSSIM based on internal generative mechanism is proposed, combining with Human Visual System (HVS). Firstly, internal generative mechanism based on the Piecewise AutoRegressive (PAR) model decomposes distorted image and the original image into two parts, the predicted part of image content using MSSIM algorithm assessment and image information uncertainty Part using PSNR assessment. Then, Mean Square Error is used as weight to combine the two scores to acquire the overall image quality assessmet results. Experiments performed on benchmark IQA databases demonstrate that the proposed algorithm not only has the best performance in different types of distortion, but also is better than the existing algorithms. -
ZHANG L, ZHANG D, MOU X, et al. FSIM: a feature similarity index for image quality assessment[J]. IEEE Transactions on Image Processing, 2011, 20(8): 2378-2386. 趙巖, 孟麗茹, 王世剛, 等. 符合人眼視覺(jué)感知特性的改進(jìn)PSNR評(píng)價(jià)方法[J]. 吉林大學(xué)學(xué)報(bào): 工學(xué)版, 2015, 45(1): 309-313. ZHAO Yan, MENG Liru, WANG Shigang, et al. Improved PSNR assessment method according with human visual perception characteristics[J]. Journal of Jilin University (Engineering and Technology Edition), 2015, 45(1): 309-313. 蔣剛毅, 黃大江, 王旭, 等. 圖像質(zhì)量評(píng)價(jià)方法研究進(jìn)展[J]. 電子與信息學(xué)報(bào), 2010, 32(1): 219-226. doi: 10.3724/SP.J. 1146.2009.00091. JIANG Gangyi, HUANG Dajiang, WANG Xu, et al. Research advancement on image quality assessment methods[J]. Journal of Electronics Information Technology, 2010, 32(1): 219-226. doi: 10.3724/SP.J.1146. 2009. 00091. DAMERA-VENKATA N, KITE T D, GEISLER W S, et al. Image quality assessment based on a degradation model[J]. IEEE Transactions on Image Processing, 2000, 9(4): 636-650. CHANDLER D M and HEMAMI S S. VSNR: a wavelet-based visual signal-to-noise ratio for natural images[J]. IEEE Transactions on Image Processing, 2007, 16(9): 2284-2298. WANG Z, BOVIK A C, SHEIKH H R, et al. Image quality assessment: from error visibility to structural similarity[J]. IEEE Transactions on Image Processing, 2004, 13(4): 600-612. WANG Z, SIMONCELLI E P, and BOVIK A C. Multi-scale structural similarity for image quality assessment[C]. Proceedings of the 37th IEEE Asilomar Conference on Signals, Systems and Computers. Pacific Grove, CA, 2003: 1398-1402. 靳鑫, 蔣剛毅, 陳芬, 等. 基于結(jié)構(gòu)相似度的自適應(yīng)圖像質(zhì)量評(píng)價(jià)[J]. 光電子 . 激光. 2014, 25(2): 378-385. JIN Xin, JIANG Gangyi, CHEN Fen, et al. Adaptive image quality assessment based on structural similarity[J]. Journal of Optoelectronics Laser, 2014, 25(2): 378-385. KNILL D C and POUGET R. The Bayesian brain: the role of uncertainty in neural coding and computation[J]. Trends in Neuroscience, 2004, 27(12): 712-719. FRISTON K. The free-energy principle: a unified brain theory?[J]. Nature Reviews Neuroscience, 2010, 11(2): 127-138. ZHAI G, WU X, YANG X, et al. A psychovisual quality metric in Free-Energy principle[J]. IEEE Transactions on Image Processing, 2012, 21(1): 41-52. WU J J, LIN W S, and SHI G G. Perceptual quality metric with internal generative mechanism[J]. IEEE Transactions on Image Processing, 2013, 22(1): 43-54. ZHENG K H, YU M, JIN X, et al. New reduced-reference objective stereo image quality assessment model based on human visual system[C]. 2014 3DTV-Conference: The True Vision-Capture, Transmission and Display of 3D Video (3DTV-CON 2014), 2014: 1-4. WU J J, LIN W S, and SHU G M. Visual masking estimation based on structural uncertainty[C]. IEEE International Symposium on Circuits and Systems (ISCAS), Beijing, 2013: 933-936. 張艷, 安平, 尤志翔, 等. 基于邊緣差異的虛擬視圖像質(zhì)量評(píng)價(jià)方法[J]. 電子與信息學(xué)報(bào), 2013, 35(8): 1894-1900. doi: 10. 3724/SP.J.1146.2012.01475. ZHANG Yan, AN Ping, YOU Zhi-xiang, et al. Quality assessment for virtual view image based on edge difference[J]. Journal of Electronics Information Technology, 2013, 35(8): 1894-1900. doi: 10.3724/SP.J.1146.2012.01475. YANG X K, LING W S, LU Z K, et al. Just noticeable distortion model and its applications in video coding[J]. Signal Processing: Image Communication, 2005, 20(7): 662-680. 南棟, 畢篤彥, 查宇飛, 等. 基于參數(shù)估計(jì)的無(wú)參考型圖像質(zhì)量評(píng)價(jià)算法[J]. 電子與信息學(xué)報(bào), 2013, 35(9): 2066-2072. doi: 10. 3724/SP.J.1146.2012.01652. NAN Dong, BI Duyan, ZHA Yufei, et al. A no-reference image quality assessment method based on parameter estimation[J]. Journal of Electronics Information Technology, 2013, 35(9): 2066-2072. doi: 10.3724/SP.J. 1146. 2012.01652. LUKIN N P V, ZELENSKY A, CARLI M, et al. Tid2008-a database for evaluation of full reference visual quality assessment metrics[J]. Advances of Modern Radio Electronics, 2009, 10(5): 30-45. -
計(jì)量
- 文章訪問(wèn)數(shù): 1290
- HTML全文瀏覽量: 141
- PDF下載量: 498
- 被引次數(shù): 0
下載:
