Abstract
It is well known that the images suffer from blocking artifacts when compressed by JPEG at low quality factors. Since JPEG uses a standard block size of 8×8 pixels, then the locations of blocking artifacts are known and occur at the boundaries of multiples of 8th pixel positions in horizontal and vertical directions. There exist a number of state-of-the-art algorithms capable of estimating the blockiness in the image for such situations. However, when an image is arbitrarily cropped or resized, the locations of block boundaries and block size are unknown and the existing block-based algorithms either fail or are not robust. For such situations, a simple no-reference method in pixel-domain is proposed in this paper. It is based on the observation that the ratio of inter-block pixel difference to the average of the two neighbouring intra-block pixel differences is likely to be higher for images compressed at lower quality factor. Therefore, the average of this ratio computed across the image is an indicator of strength of blockiness and is used as a quality metric. Unlike existing algorithms, the proposed method can be applied to images with known as well as unknown block boundaries and is robust to block misalignment making it capable of measuring the blockiness even in arbitrarily cropped and resized images. The Spearman’s-rank-order-correlation-coefficient between the quality score and subjective rating of images is computed for seven standard image databases. It is observed that the proposed method gives consistent performance with higher correlation values than most of the competitive state-of-the-art blockiness measuring algorithms. The computational complexity analysis shows that despite the high accuracy, the proposed method has lower complexity.
Similar content being viewed by others
Data Availability
All the image databases used during this study are publicly available. Additional data if required will be made available on reasonable request.
References
Babu RV, Suresh S, Perkis A (2007) No-reference jpeg-image quality assessment using GAP-RBF. Signal Process 87(6):1493–1503
Chen C, Bloom JA (2010) A blind reference-free blockiness measure. In: Pacific-rim conference on multimedia. Springer, pp 112–123
Corchs S, Gasparini F, Schettini R (2014) No reference image quality classification for JPEG-distorted images. Digital Signal Process 30:86–100
Fang R, Al.bayaty R, Wu D (2016) BNB method for no-reference image quality assessment. IEEE Trans Circuits Syst Video Technol 27(7):1381–1391
Golestaneh SA, Chandler DM (2013) No-reference quality assessment of JPEG images via a quality relevance map. IEEE Signal Process Lett 21(2):155–158
Gu K, Zhai G, Lin W, Yang X, Zhang W (2015) No-reference image sharpness assessment in autoregressive parameter space. IEEE Trans Image Process 24(10):3218–3231
Gu K, Zhai G, Yang X, Zhang W (2014) ‘Using free energy principle for blind image quality assessment’. IEEE Trans Multimed 17(1):50–63
Gunawan IP, Ghanbari M (2008) Efficient reduced-reference video quality meter. IEEE Trans Broadcast 54(3):669–679
Larson E, Chandler D (2009) Categorical image quality (CSIQ) database. http://vision.okstate.edu/csiq
Le.Callet P, Autrusseau F (2005) Subjective quality assessment IRCCYN/IVC database. http://www.irccyn.ec-nantes.fr/ivcdb/
Lee S, Park SJ (2012) A new image quality assessment method to detect and measure strength of blocking artifacts. Signal Process Image Commun 27 (1):31–38
Li L, Zhou Y, Wu J, Lin W, Li H (2015) GridSAR: grid strength and regularity for robust evaluation of blocking artifacts in jpeg images. J Vis Commun Image Rep 30:153–163
Li L, Zhu H, Yang G, Qian J (2013) Referenceless measure of blocking artifacts by Tchebichef kernel analysis. IEEE Signal Process Lett 21(1):122–125
Lim CL, Paramesran R, Jassim WA, Yu YP, Ngan K (2016) N: blind image quality assessment for Gaussian blur images using exact Zernike moments and gradient magnitude. J Frankl Inst 353(17):4715–4733
Liu H, Heynderickx I (2009) A perceptually relevant no-reference blockiness metric based on local image characteristics. EURASIP J Adv Signal Process, (1), pp 263540
Liu L, Liu B, Huang H, Bovik AC (2014) No-reference image quality assessment based on spatial and spectral entropies. Signal Process Image Commun 29(8):856–863
Meesters L, Martens JB (2002) A single-ended blockiness measure for JPEG-coded images. Signal Process 82(3):369–387
Mittal A, Moorthy AK, Bovik AC (2012) No-reference image quality assessment in the spatial domain. IEEE Trans Image Process 21(12):4695–4708
Mittal A, Soundararajan R, Bovik AC (2012) Making a “completely blind” image quality analyzer. IEEE Signal Process 20(3):209–212
Nafchi HZ, Shahkolaei A, Hedjam R, Cheriet M (2016) MUG: a parameterless no-reference jpeg quality evaluator robust to block size and misalignment. IEEE Signal Process Lett 23(11):1577–1581
Nakhaei AA, Helfroush MS, Danyali H, Ghanbari M (2018) Subjectively correlated estimation of noise due to blurriness distortion based on auto-regressive model using the Yule–Walker equations. IET Image Process 12(10):1788–1796
Pan F, Lin X, Rahardja S, Lin W, Ong E, Yao S et al (2004) A locally-adaptive algorithm for measuring blocking artifacts in images and videos. In: 2004 IEEE international symposium on circuits and systems. IEEE, vol 3, pp III–925
Ponomarenko N, Carli M, Lukin V, Egiazarian K, Astola J, Battisti F (2008) Tampere image database. http://www.ponomarenko.info/tid2008.htm
Ponomarenko N, Jin L, Ieremeiev O, Lukin V, Egiazarian K, Astola J et al (2015) Image database TID2013: peculiarities, results and perspectives. Signal Process Image Commun 30:57–77
Saad MA, Bovik AC, Charrier C (2012) ‘Blind image quality assessment: a natural scene statistics approach in the DCT domain’. IEEE Trans Image Process 21(8):3339–3352
Saha A, Wu QMJ (2015) Utilizing image scales towards totally training free blind image quality assessment. IEEE Trans Image Process 24(6):1879–1892
Sheikh H (2005) LIVE image quality assessment database release 2. http://live.ece.utexas.edu/research/quality
Sheikh HR, Sabir MF, Bovik AC (2006) A statistical evaluation of recent full reference image quality assessment algorithms. IEEE Trans Image Process 15(11):3440–3451
Tan K, Ghanbari M (2000) ‘Blockiness detection for MPEG2-coded video’. IEEE Signal Process Lett 7(8):213–215
Tang C, Wang B (2016) A no-reference adaptive blockiness measure for JPEG compressed images. PloS One 11(11):e0165664
Venkatanath N, Praneeth D, Bh MC, Channappayya SS, Medasani SS (2015) Blind image quality evaluation using perception based features. In: 2015 Twenty first national conference on communications (NCC). IEEE, pp 1–6
Wang Z (2016) Objective image quality assessment: facing the real-world challenges. Electr Imaging 13:1–6
Wang Z, Bovik AC (2006) Modern image quality assessment. Synthesis Lect Image Video Multimed Process 2(1):1–156
Wang Z, Bovik AC, Evan BL (2000) Blind measurement of blocking artifacts in images. In: Proceedings 2000 international conference on image processing. IEEE, vol 3, pp 981–984
Wang Z, Sheikh HR, Bovik AC (2002) No-reference perceptual quality assessment of JPEG compressed images. In: Proceedings. international conference on image processing. IEEE, vol 1, pp 1–1
Wu HR, Yuen M (1997) A generalized block-edge impairment metric for video coding’. IEEE Signal Process Lett 4(11):317–320
Wu J, Zeng J, Dong W, Shi G, Lin W (2019) Blind image quality assessment with hierarchy: degradation from local structure to deep semantics. Elsevier J Vis Commun Image Rep 58:353–362
Xue W, Mou X, Zhang L, Bovik AC, Feng X (2014) Blind image quality assessment using joint statistics of gradient magnitude and Laplacian features. IEEE Trans Image Process 23(11):4850–4862
Yang C, Zhang X, An P, Shen L, Kuo CCJ (2021) Blind image quality assessment based on multi-scale KLT. IEEE Trans Multimed 23:1557–1566
Zarić A, Tatalović N, Brajković N, Hlevnjak H, Lončarić M, Dumić E et al (2012) VCL@ Fer image quality assessment database. AUTOMATIKA: č,asopis za automatiku, mjerenje, elektroniku, računarstvo i komunikacije 53(4):344–354
Zhan Y, Zhang R (2017) No-reference JPEG image quality assessment based on blockiness and luminance change. IEEE Signal Process Lett 24(6):760–764
Acknowledgements
This publication is an outcome of the R&D project carried out under the Visvesvaraya PhD scheme (Unique Awardee Number is MEITY-PHD-562) of MeitY, Government of India. The MATLAB P-files of the proposed method are publicly available at https://github.com/MdAmirBaig/IQA-of-JPEG-compressed-image.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of Interests
The authors declare that they have no conflict of interest.
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Baig, M.A., Moinuddin, A.A., Khan, E. et al. A versatile blind JPEG image quality assessment method. Multimed Tools Appl 82, 36395–36412 (2023). https://doi.org/10.1007/s11042-023-14983-0
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-023-14983-0