Abstract
We propose a framework to combine various quality metrics using a full reference approach for High Dynamic Range (HDR) Image quality assessment (IQA). We combine scores from metrics exclusively designed for different applications such as HDR, Standard Dynamic Range (SDR) and color difference measures, in a non-linear manner using machine learning (ML) approaches with weights determined during an offline training process. We explore various ML techniques and find that support vector machine regression and gradient boosting regression trees are effective. To improve performance and reduce complexity, we use the back-tracking based Sequential Floating Forward Selection technique during training to include a subset of metrics from a list of quality metrics in our model. We evaluate the performance on five publicly available calibrated HDR databases with different types of distortion (including different types of compression, Gaussian noise, gamut mismatch, chromatic distortions and so on) and demonstrate improved performance using our method as compared to several existing IQA metrics. We perform extensive statistical analysis to demonstrate significant improvement over existing approaches and show the generality and robustness of our approach using cross-database validation.
Similar content being viewed by others
Notes
We use the terms LDR and SDR interchangeably in this paper
References
BT (2016) 2100: Image parameter values for high dynamic range television for use in production and international programme exchange. International Telecommunication Union
Aydin T, Mantiuk R, Myszkowski K, Seidel HP (2008) Dynamic range independent image quality assessment. ACM Trans Graph 27(3):69:1–69:10
Azimi M, Banitalebi-Dehkordi A, Dong Y, Pourazad M, Nasiopoulos P (2014) Evaluating the performance of existing full-reference quality metrics on high dynamic range HDR video content. In: International conference on multimedia signal processing
Basak D, Pal S, Patranabis D (2007) Support vector regression. In: Neural information processing letters and reviews, pp. 203–224
Bovik AC, Sheikh HR, Simoncelli EP (2004) Image quality assessment: from error visibility to structural similarity. IEEE Trans Image Process 13(4):600–612
Breiman L (2001) Random forests. Machine Learning 45(1):5–32
Breiman L, Friedman J, Olshen R, Stone C (1984) Classification and regression trees. Wadsworth and brooks, monterey CA
Choudhury A, Daly S (2018) HDR image quality assessment using machine-learning based combination of quality metrics. In: 2018 IEEE global conference on signal and information processing (GlobalSIP), Anaheim, CA, USA, pp 91–95
Choudhury A, Daly S (2019) Combining quality metrics for improved HDR image quality assessment. In: 2Nd IEEE conference on multimedia information processing and retrieval, MIPR 2019, san jose, CA, USA, March 28-30, 2019, pp. 179–184
Choudhury A, Daly S (2019) Combining quality metrics using machine learning for improved and robust HDR image quality assessment. Electronic Imaging 2019 (10):307–1–307-7. https://doi.org/10.2352/ISSN.2470-1173.2019.10.IQSP-307
Choudhury A, Pytlarz J, Daly S (2019) HDR And WCG image quality assessment using color difference metrics. In: SMPTE 2019 Annual technical conference and exhibition
Cortes C, Vapnik V (1995) Support-vector networks. Mach Learn 20(3):273–297
Duda RO, Hart PE, Stork DG (2000) Pattern classification 2Nd edition. Wiley-interscience, new york, NY USA
Freitas PG, Akamine WYL, Farias MCQ (2018) No-reference image quality assessment using orthogonal color planes patterns. IEEE Transactions on Multimedia 20(12):3353–3360
Friedman JH (1997) On bias, variance, 0/1—loss, and the curse-of-dimensionality. Data Min Knowl Disc 1(1):55–77
Friedman JH (2000) Greedy function approximation: a gradient boosting machine. Ann Stat 29:1189–1232
Friedman JH (2002) Stochastic gradient boosting. Comput Stat Data Anal 38 (4):367–378
Goodfellow I, Bengio Y, Courville A (2016) Deep Learning MIT Press . http://www.deeplearningbook.org
Gu K, Zhai G, Yang X, Zhang W (2013) A new psychovisual paradigm for image quality assessment: from differentiating distortion types to discriminating quality conditions. SIViP 7(3):423–436
Gu K, Zhai G, Yang X, Zhang W (2015) Using free energy principle for blind image quality assessment. IEEE Transactions on Multimedia 17(1):50–63
Guan F, Jiang G, Song Y, Yu M, Peng Z, Chen F (2018) No-reference high-dynamic-range image quality assessment based on tensor decomposition and manifold learning. Applied Optics 57:839
Hanhart P, Bernardo M, Pereira M, Pinheiro AMG, Ebrahimi T (2015) Benchmarking of objective quality metrics for HDR image quality assessment. EURASIP Journal on Image and Video Processing 2015(1):39
Hanhart P, Rerabek M, Ebrahimi T (2016) Subjective and objective evaluation of hdr video coding technologies. In: Qo MEX, pp. 1–6
ITU-R BT (2019) 2124-0: Objective metric for the assessment of the potential visibility of colour differences in television
ITU-T (2012) Methods, metrics and procedures for statistical evaluation, qualification and comparison of objective quality prediction models
Jia S, Zhang Y, Agrafiotis D, Bull D (2017) Blind high dynamic range image quality assessment using deep learning. In: IEEE ICIP, pp. 765–769
Korshunov P, Hanhart P, Richter T, Artusi A, Mantiuk R, Ebrahimi T (2015) Subjective quality assessment database of HDR images compressed with jpeg xt. In: QoMEX, pp 1–6
Kuang J, Johnson GM, Fairchild MD (2007) icam06: A refined image appearance model for hdr image rendering. Journal of Visual Communication and Image Representation 18(5), 406–414. Special issue on High Dynamic Range Imaging
Li Z, Aaron A, Katsavounidis I, Moorthy A, Manohara M. (2016) Toward a practical perceptual video quality metric
Li Z, Norkin A, Aaron A (2016) VMAF - Video quality metric alternative to PSNR Joint Video Exploration Team JVET of ITU-T SG 16 WP 3 and ISO/IEC JTC 1/SC 29/WG, 11
Lin CY, Jheng KR, Shih T (2018) Objective hdr image quality assessment. Multimedia Tools and Applications 78:1–21
Lin JY, Liu TJ, Wu ECH, Kuo CCJ (2014) A fusion-based video quality assessment fvqa index. In: Signal and information processing association annual summit and conference (APSIPA), pp 1–5
Liu TJ, Lin W, Kuo CCJ (2013) Image quality assessment using multi-method fusion. IEEE Trans Image Process 22(5):1793–1807
Luo MR, Cui G, Rigg B (2001) The development of the CIE 2000 colour-difference formula: CIEDE 2000. Color Research & Application 26(5):340–350
Ma L, Li S, Zhang F, Ngan KN (2011) Reduced-reference image quality assessment using reorganized dct-based image representation. IEEE Transactions on Multimedia 13(4):824–829
Mai Z, Mansour H, Mantiuk R, Nasiopoulos P, Ward R, Heidrich W (2011) Optimizing a tone curve for backward-compatible high dynamic range image and video compression. IEEE Trans Image Process 20(6):1558–1571
Mantiuk R, Kim KJ, Rempel AG, Heidrich W (2011) HDR-VDP,-2: A calibrated visual metric for visibility and quality predictions in all luminance conditions. ACM Trans Graph 30(4):40:1–40:14
Mantiuk R, Myszkowski K, Seidel HP (2006) A perceptual framework for contrast processing of high dynamic range images. ACM Trans. Appl Percept 3 (3):286–308
Miller S, Nezamabadi M, Daly S (2012) Perceptual signal coding for more efficient usage of bit codes The 2012 annual technical conference exhibition, pp 1–9
Mittal A, Moorthy AK, Bovik AC (2012) No-reference image quality assessment in the spatial domain. IEEE Trans Image Process 21(12):4695–4708
Moorthy A, Bovik A (2011) Visual quality assessment algorithms: What does the future hold Multimedia Tools and Applications 51:675–696
Moorthy AK, Bovik AC (2011) Blind image quality assessment: from natural scene statistics to perceptual quality. IEEE Trans Image Process 20(12):3350–3364
Nafchi HZ, Shahkolaei A, Hedjam R, Cheriet M (2016) Mean deviation similarity index: Efficient and reliable full-reference image quality evaluator. IEEE Access 4:5579–5590
Nafchi HZ, Shahkolaei A, Moghaddam RF, Cheriet M (2015) FSITM: A feature similarity index for tone-mapped images. IEEE Signal Processing Letters 22 (8):1026–1029
Narwaria M, Mantiuk R, Silva MPD, Callet PL (2015) HDR-VDP-2.2:A calibrated method for objective quality prediction of high-dynamic range and standard images. J Electron Imaging 24(24–24):3
Narwaria M, Perreira Da Silva M, Le Callet P, Pepion R (2013) Tone mapping-based high-dynamic-range image compression: Study of optimization criterion and perceptual quality. Opt Eng 102008:52
Narwaria M, Silva MPD, Callet PL (2015) HDR - VQM: An objective quality measure for high dynamic range video. Signal Processing:, Image Communication 35:46–60
Pieri E, Pytlarz J (2017) Hitting the mark - a new color difference metric for hdr and wcg imagery. In: SMPTE 2017 Annual technical conference and exhibition, pp. 1–13
Pudil P, Novovičová J., Kittler J (1994) Floating search methods in feature selection. Pattern Recogn Lett 15(11):1119–1125
Rehman A, Wang Z (2012) Reduced-reference image quality assessment by structural similarity estimation. IEEE Trans Image Process 21(8):3378–3389
Reinhard E, Stark M, Shirley P, Ferwerda J (2002) Photographic tone reproduction for digital images. ACM Trans Graph 21(3):267–276
Rousselot M, Auffret E, Ducloux X, Le Meur O, Cozot R (2018) Impacts of viewing conditions on hdr-vdp2. In: EUSIPCO, pp. 1442–1446
Rousselot M, Le Meur O, Cozot R, Ducloux X (2019) Quality assessment of hdr/wcg images using hdr uniform color spaces Journal of Imaging 5(1)
Rumelhart DE, Hinton GE, Williams RJ (1986) In: Parallel Distributed processing: Explorations in the Microstructure of Cognition, Vol. 1, chap Learning Internal Representations by Error Propagation, pp. 318–362. MIT Press, Cambridge, MA USA
Sheikh HR, Bovik AC (2002) No-reference perceptual quality assessment of jpeg compressed images. In: International conference on image processing, pp. 477–480
Sheikh HR, Bovik AC (2006) Image information and visual quality. IEEE TIP 15(2):430–444
Sheikh HR, Bovik AC, de Veciana G (2005) An information fidelity criterion for image quality assessment using natural scene statistics. IEEE Transactions on Image Processing 14(12):2117–2128
Aydin TR, Mantiuk HS (2008) Extending quality metrics to full luminance range images. pp. 6806–6806 – 10
Valenzise G, Simone FD, Lauga P, Dufaux F (2014) Performance evaluation of objective quality metrics for hdr image compression. In: SPIE Optical engineering + applications, international society for optics and photonics
Ververidis D, Kotropoulos C (2005) Sequential forward feature selection with low computational cost. In: 13Th european signal processing conference, pp. 1–4
VQEG (2003) Final report from the video quality experts group on the validation of objective models of video quality assessment
Wang Z, Bovik AC (2002) A universal image quality index. IEEE Signal Processing Letters 9(3):81–84
Wang Z, Simoncelli EP (2005) Reduced-reference image quality assessment using a wavelet-domain natural image statistic model. In: SPIE Human vision and electronic imaging, vol. 5666, pp. 149–159
Wang Z, Simoncelli EP, Bovik AC (2003) Multiscale structural similarity for image quality assessment. In: 37Th asilomar conference on signals, systems and computers, vol. 2, pp. 1398–1402. IEEE
Whitney AW (1971) A direct method of nonparametric measurement selection. IEEE Transactions on Computers C-20(9):1100–1103
Wu Q, Li H, Wang Z, Meng F, Luo B, Li W, Ngan KN (2017) Blind image quality assessment based on rank-order regularized regression. IEEE Transactions on Multimedia 19(11):2490–2504
Xue W, Zhang L, Mou X, Bovik AC (2014) Gradient magnitude similarity deviation: a highly efficient perceptual image quality index. IEEE Trans Image Process 23(2):684–695
Yu H, He F, Yiteng P (2019) A scalable region-based level set method using adaptive bilateral filter for noisy image segmentation. Multimedia Tools and Applications 79:5743–5765
Zerman E, Valenzise G, Dufaux F (2017) An extensive performance evaluation of full-reference HDR image quality metrics. Quality and User Experience 2(1):5
Zhang J, He F, Chen Y (2019) A new haze removal approach for sky/river alike scenes based on external and internal clues. Multimedia Tools and Applications 79:2085–2107
Zhang L, Zhang L, Mou X, Zhang D (2011) FSIM: A feature similarity index for image quality assessment. IEEE TIP 20(8):2378–2386
Ziaei Nafchi H, Cheriet M (2018) Efficient no-reference quality assessment and classification model for contrast distorted images. IEEE Trans Broadcast 64(2):518–523
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Choudhury, A. Robust HDR image quality assessment using combination of quality metrics. Multimed Tools Appl 79, 22843–22867 (2020). https://doi.org/10.1007/s11042-020-08985-5
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-020-08985-5