融合人眼掩蔽效应和图像梯度的块效应评价方法
|
摘要
针对JPEG格式的图像采用分块离散余弦变换的压缩方式易产生块效应的情况,提出了一种高效的无参考块效应评价方法.首先,对图像块边界处像素点的梯度进行变换得到图像块效应映射图(主要包括图像块效应边界的位置和强度信息);然后,计算人眼对图像的亮度和纹理掩蔽效应,将其结合到块效应映射图中,得到显著性块效应映射图,并使用Minkowski法计算出图像块效应评价指标;最后,在LIVE等图像质量评价数据库中进行了大量的试验仿真.仿真结果中单调一致性指标——SROCC和KROCC分别达到了0.9、0.7以上.
Blocking artifacts were the result of block-based discrete cosine transform in JPEG coding.An efficient no-reference method to measure the blocking artifacts was proposed in this paper. Firstly, the gradient of the pixels at block boundaries was transformed into the blocking artifact map,which mainly included the positions and intensity information of blocking artifact boundaries. Then the effects of luminance and texture masking on blocking were figwredout and integrated into the blocking artifact map to form an noticeable blocking artifacts map. Based on the noticeable blocking artifacts map, the Minkowski method was used to calculate the metric of image blocking artifacts.Finally, a large number of experimental simulations were performed in LIVE and other image quality assessment databases. The simulation results showed that SROCC and KROCC reached 0.9, 0.7 or more.
Blocking artifacts were the result of block-based discrete cosine transform in JPEG coding.An efficient no-reference method to measure the blocking artifacts was proposed in this paper. Firstly, the gradient of the pixels at block boundaries was transformed into the blocking artifact map,which mainly included the positions and intensity information of blocking artifact boundaries. Then the effects of luminance and texture masking on blocking were figwredout and integrated into the blocking artifact map to form an noticeable blocking artifacts map. Based on the noticeable blocking artifacts map, the Minkowski method was used to calculate the metric of image blocking artifacts.Finally, a large number of experimental simulations were performed in LIVE and other image quality assessment databases. The simulation results showed that SROCC and KROCC reached 0.9, 0.7 or more.
引文
[1] 张卫党,吴琳.基于喷泉码及CDMA扩频的数字水印盲算法[J].郑州大学学报(工学版),2017,38(6):23-28.
[2] GU K, LI L D, LU H, et al. A fast reliable image quality predictor by fusing micro-and macro-structures[J].IEEE transactions on industrial electronics, 2017,64(5): 3903-3912.
[3] LIU L X, LIU B, HUANG H, et al. No-reference image quality assessment based on spatial and spectral entropies[J]. Signal processing: image communication, 2014, 29(8): 856-863.
[4] RYU S, SOHN K. Blind blockiness measure based on marginal distribution of wavelet coefficient and saliency [C]//IEEE International Conference on Acoutics Speech and Signal Processing. Vancouver, BC: IEEE, 2013:1874-1878.
[5] 王璐烽, 刘辉元. 基于机器学习的图像块效应盲评价算法[J]. 重庆邮电大学学报(自然科学版), 2014, 26(6):856-860.
[6] WINKLER S. Quality metric design: a closer look [C]//SPIE 3939 Human Vision and Electronic Imaging V. San Jose: SPIE, 2000: 37-44.
[7] ZHAI G, ZHANG W, YANG X, et al. No-reference noticeable blockiness estimation in images[J]. Signal processing: image communication, 2008, 23(6):417-432.
[8] LIEW A W C, YAN H. Blocking artifacts suppression in block-coded images using overcomplete wavelet representation[J]. IEEE transactions on circuits & systems for video technology, 2004, 14(4):450-461.
[9] TONG H H Y, VENETSANOPOULOS A N. A perceptual model for JPEG applications based on block classification, texture masking, and luminance masking[C]//1998 International Conterence on Image Processing. Chicago: IEEE, 1998: 428-432.
[10] CHOU C H, LI Y C. A perceptually tuned subband image coder based on the measure of just-noticeable-distortion profile[J]. IEEE transactions on circuits & systems for video technology, 1995, 5(6):467-476.
[11] CALLET P L, AUTRUSSEAU F. Subjective quality assessment IRCCyN/IVC database[DB/OL]. (2015-02-04).[2018-05-04].http://www.irccyn. ecnantes.fr/ivcdb/.
[12] SHEIKH H R, WANG Z, CORMACK L, et al.LIVE image quality assessment database Release2[EB/OL].(2005-06-16).[2018-05-04]. http://live.ece.utexas.edu/research/quality.
[13] PONOMARENKO N, LUKIN V, ZELENSKY A, et al.TID2008-A database for evaluation of full-reference visual quality assessment metrics[J]. Adv modern ra-dioelectron, 2009,10:30-45.
[14] MITTAL A, MOORTHY A K, BOVIK A C. Blind/referenceless image spatial quality evaluator[C]//2011 Conference Record of the Forty-fifth Asilomar Coference on Signals Systems and Computes. Pacific Grover, CA: IEEEE, 2011:723-727.
[15] MITTAL A, MOORTHY A K, BOVIK A C. No-reference image quality assessment in the spatial domain[J]. IEEE transactions on image processing, 2012, 21(12):4695-4708.
[16] WANG Z, SHEIKH H R, BOVIK A C. No-reference perceptual quality assessment of JPEG compressed images[C]//International Conference on Image Processing. Rochester, NY: IEEE, 2002: 477-480.
[17] LEE S, PARK S J. A new image quality assessment method to detect and measure strength of blocking artifacts[J]. Signal processing: image communication, 2012, 27: 31-38.
[18] 王志明. 无参考图像质量评价综述[J]. 自动化学报,2015,41(6):1062-1079.
[2] GU K, LI L D, LU H, et al. A fast reliable image quality predictor by fusing micro-and macro-structures[J].IEEE transactions on industrial electronics, 2017,64(5): 3903-3912.
[3] LIU L X, LIU B, HUANG H, et al. No-reference image quality assessment based on spatial and spectral entropies[J]. Signal processing: image communication, 2014, 29(8): 856-863.
[4] RYU S, SOHN K. Blind blockiness measure based on marginal distribution of wavelet coefficient and saliency [C]//IEEE International Conference on Acoutics Speech and Signal Processing. Vancouver, BC: IEEE, 2013:1874-1878.
[5] 王璐烽, 刘辉元. 基于机器学习的图像块效应盲评价算法[J]. 重庆邮电大学学报(自然科学版), 2014, 26(6):856-860.
[6] WINKLER S. Quality metric design: a closer look [C]//SPIE 3939 Human Vision and Electronic Imaging V. San Jose: SPIE, 2000: 37-44.
[7] ZHAI G, ZHANG W, YANG X, et al. No-reference noticeable blockiness estimation in images[J]. Signal processing: image communication, 2008, 23(6):417-432.
[8] LIEW A W C, YAN H. Blocking artifacts suppression in block-coded images using overcomplete wavelet representation[J]. IEEE transactions on circuits & systems for video technology, 2004, 14(4):450-461.
[9] TONG H H Y, VENETSANOPOULOS A N. A perceptual model for JPEG applications based on block classification, texture masking, and luminance masking[C]//1998 International Conterence on Image Processing. Chicago: IEEE, 1998: 428-432.
[10] CHOU C H, LI Y C. A perceptually tuned subband image coder based on the measure of just-noticeable-distortion profile[J]. IEEE transactions on circuits & systems for video technology, 1995, 5(6):467-476.
[11] CALLET P L, AUTRUSSEAU F. Subjective quality assessment IRCCyN/IVC database[DB/OL]. (2015-02-04).[2018-05-04].http://www.irccyn. ecnantes.fr/ivcdb/.
[12] SHEIKH H R, WANG Z, CORMACK L, et al.LIVE image quality assessment database Release2[EB/OL].(2005-06-16).[2018-05-04]. http://live.ece.utexas.edu/research/quality.
[13] PONOMARENKO N, LUKIN V, ZELENSKY A, et al.TID2008-A database for evaluation of full-reference visual quality assessment metrics[J]. Adv modern ra-dioelectron, 2009,10:30-45.
[14] MITTAL A, MOORTHY A K, BOVIK A C. Blind/referenceless image spatial quality evaluator[C]//2011 Conference Record of the Forty-fifth Asilomar Coference on Signals Systems and Computes. Pacific Grover, CA: IEEEE, 2011:723-727.
[15] MITTAL A, MOORTHY A K, BOVIK A C. No-reference image quality assessment in the spatial domain[J]. IEEE transactions on image processing, 2012, 21(12):4695-4708.
[16] WANG Z, SHEIKH H R, BOVIK A C. No-reference perceptual quality assessment of JPEG compressed images[C]//International Conference on Image Processing. Rochester, NY: IEEE, 2002: 477-480.
[17] LEE S, PARK S J. A new image quality assessment method to detect and measure strength of blocking artifacts[J]. Signal processing: image communication, 2012, 27: 31-38.
[18] 王志明. 无参考图像质量评价综述[J]. 自动化学报,2015,41(6):1062-1079.