Blind image quality assessment (BIQA) aims to evaluate the quality of an image without information regarding its reference image. In this paper, we proposed a novel BIQA method, which combines thirty six natural scene statistics (NSS) features, two color statistics features and four perceptual features to construct an image quality assessment model. Support Vector Regression (SVR) is adopted to build the relationship between these features and image quality scores, yielding a measure of image quality. Experimental results in LIVE, TID2013 databases and their cross validations show that the proposed method records a higher correlations with human subjective judgments of visual quality and delivers highly competitive performance with state-of-the-art BIQA models.
WangZ., BovikA.C., EvanB.L., Blind measurement of blocking artifacts in images, in Proc IEEE Int Conf Image Process, 2000, pp. 981–984.
9.
PanF., et al., A locally adaptive algorithm for measuring blocking artifacts in images and videos, Signal Process, Image Commun19(6) (2004), 499–506.
10.
LiuH., KlompN., HeynderickxI., A no-reference metric for perceived ringing artifacts in images, IEEE Trans Circuits Syst Video Technol Technol20(4) (2010), 529–539.
11.
FerzliR., KaramL.J., A no-reference objective image sharpness metric based on the notion of just noticeable blur (JNB), IEEE Trans Image Process18(4) (2009), 717–728.
12.
VaradarajanS., KaramL.J., An improved perception-based noreference objective image sharpness metric using iterative edge refinement, in Proc 15th IEEE Int Conf Image Process, 2008, pp. 401–404.
13.
SheikhH.R., BovikA.C., CormackL., No-reference quality assessment using natural scene statistics: JPEG2000, IEEE Trans Image Process14(11) (2005), 1918–1927.
14.
BabuR.V., SureshS., PerkisA., No-reference JPEG-image quality assessment using GAP-RBF, Signal Process87(6) (2007), 1493–1503.
15.
SazzadZ.M.P., KawayokeY., HoritaY., No reference image quality assessment for JPEG2000 based on spatial features, Signal Process, Image Commun23(4) (2008), 257–268.
16.
LiangL., WangS., ChenJ., MaS., ZhaoD., GaoW., No-reference perceptual image quality metric using gradient profiles for JPEG2000, Signal Process, Image Commun25(7) (2010), 502–516.
17.
MoorthyA.K., BovikA.C., A two-step framework for constructing blind image quality indices, IEEE Signal Process Lett17(5) (2010), 513–516.
18.
MittalA., MoorthyA.K., BovikA.C., No-reference image quality assessment in the spatial domain, IEEE Trans Image Process21(12) (2012), 4695–4708.
19.
SaadM.A., BovikA.C., CharrierC., Blind image quality assessment: A natural scene statistics approach in the DCT domain, IEEE Trans Image Process21(8) (2012), 3339–3352.
20.
MoorthyA.K., BovikA.C., Blind image quality assessment:From natural scene statistics to perceptual quality, IEEE Trans Image Process20(12) (2011), 3350–3364.
21.
TangH., JoshiN., KapoorA., Learning a blind measure of perceptual image quality, in Proc IEEE Conf Comput Vis Pattern Recognit, 2011, pp. 305–312.
22.
YeP., KumarJ., KangL., DoermannD., Unsupervised feature learning framework for no-reference image quality assessment, in Proc IEEE Conf Comput Vis Pattern Recognit, 2012, pp. 1098–1105.
23.
LiC., ZhangY., WuX., et al., Blind multiply distorted image quality assessment using relevant perceptual features, IEEE International Conference on Image Processing, 2015, pp. 4883–4886.
24.
ZhangL., ZhangL., BovikA.C., A feature-enriched completely blind image quality elevator, IEEE Transactions on Image Processing24(8) (2015), 2579–2591.
25.
MittalA., MuralidharG.S., GhoshJ., BovikA.C., Blind image quality assessment without human training using latent quality factors, IEEE Signal Process Lett19(2) (2012), 75–78.
26.
MittalA., SoundararajanR., BovikA.C., Making a completely blind image quality analyzer, IEEE Signal Process Lett20(3) (2013), 209–212.
27.
XueW., ZhangL., MouX., Learning without human scores for blind image quality assessment, in Proc IEEE Conf Comput Vis Pattern Recognit, 2013, pp. 995–1002.
28.
JongyooK., Anh-DucN., SanghoonL., Deep CNN-based blind image quality predictor[J], IEEE Transactions on Neural Networks and Learning Systems (2018), 1–14.
29.
YanQ., GongD., ZhangY., Two-stream convolutional networks for blind image quality assessment[J], IEEE Transactions on Image Processing: A Publication of the IEEE Signal Processing Society28(5) (2019), 2200.
30.
PonomarenkoN., et al., Color image database TID: Peculiarities and preliminary results, in Proc Eur Workshop Vis Inf Process, 2013, pp. 106–111.
31.
SheikhH.R., SabirM.F., BovikA.C., A statistical evaluation of recent full reference image quality assessment algorithms, IEEE Trans Image Process15(11) (2006), 3440–3451.
32.
MorroneM.C., OwensR.A., Feature detection from local energy, Pattern Recogn Lett6(5) (1987), 303–313.
33.
KovesiP., Image features from phase congruency, J Comput Vis Res1 (1999), 1–26.
34.
RudermanD.L., CroninT.W., ChiaoC.C., Statistics of cone responses to natural images: Implications for visual coding, J Opt Soc Amer A15(8) (1998), 2036–2045.
ZhangY., MoorthyA.K., ChandlerD.M., BovikA.C., C-DIIVINE: No-reference image quality assessment based on local magnitude and phase statistics of natural scenes, Signal Processing: Image Communication29(7) (2014), 725–747.
37.
LiuL.X., LiuB., HuangH., BovikA.C., No-reference image quality assessment based on spatial and spectral entropies, Signal Processing: Image Communication29(8) (2014), 856–863.
38.
LiJ.-F., No-reference image quality assessment based on natural scene statistics in RGB color space, Acta Automatica Sinica41(9) (2015), 1601–1615.
39.
LasmarN.-E., StitouY., BerthoumieuY., Multiscale skewed heavy tailed model for texture analysis, in Proc 16th IEEE Int Conf Image Process, 2009, pp. 2281–2284.
