Review: A Survey on Objective Evaluation of Image Sharpness
Source abstract
Abstract
Establishing an accurate objective evaluation metric of image sharpness is crucial for image analysis, recognition and quality measurement. In this review, we highlight recent advances in no-reference image quality assessment research, divide the reported algorithms into four groups (spatial domain-based methods, spectral domain-based methods, learning-based methods and combination methods) and outline the advantages and disadvantages of each method group. Furthermore, we conduct a brief bibliometric study with which to provide an overview of the current trends from 2013 to 2021 and compare the performance of representative algorithms on public datasets. Finally, we describe the shortcomings and future challenges in the current studies.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Image and Video Quality Assessment · Image Enhancement Techniques · Visual Attention and Saliency Detection
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
School of Textile Science and Engineering, Xi’an Polytechnic University, Xi’an 710048, China
Faculty of Engineering, The University of Sydney, Sydney, NSW 2006, Australia
Key Laboratory of Functional Textile Material and Product, Xi’an Polytechnic University, Ministry of Education, Xi’an 710048, China
Funding
National Natural Science Foundation of China · Key Research and Development Program of Shaanxi · Natural Science Basic Research Program of Shaanxi · Innovation Capability Support Program of Shaanxi · Outstanding Young Talents Support Plan of Shaanxi Universities (2020), Scientific Research Program Funded by Shaanxi Provincial Education Department · Science and Technology Guiding Project of China National Textile and Apparel Council · Innovation Capacity Support Plan of Shaanxi, China
References (100+)
Show source-provided references
1. Perceptual quality evaluation of hazy natural images10.1109/TII.2021.3065439 ↗
2. Deep-learning image reconstruction for image quality evaluation and accurate bone mineral density measurement on quantitative CT: A phantom-patient study10.3389/fendo.2022.884306 ↗
3. Color image segmentation using level set method with initialization mask in multiple color spaces
4. Proof of concept image artifact reduction by energy-modulated proton computed tomography (EMpCT)10.1016/j.ejmp.2020.12.012 ↗
5. Liu, S.Q., Yu, S., Zhao, Y.M., Tao, Z., Yu, H., and Jin, L.B. (2021). Salient region guided blind image sharpness assessment. Sensors, 21.10.3390/s21123963 ↗
6. State estimation based echolocation bionics and image processing based target pattern recognition10.25046/aj040108 ↗
7. Ke, Z.X., Yu, L.J., Wang, G., Sun, R., Zhu, M., Dong, H.R., Xu, Y., Ren, M., Fu, S.D., and Zhi, C. (2023). Three-Dimensional modeling of spun-bonded nonwoven meso-structures. Polymers, 15.10.3390/polym15030600 ↗
8. A self-pumping dressing with multiple liquid transport channels for wound microclimate management10.1002/mabi.202200356 ↗
9. Reduced- and no-reference image quality assessment10.1109/MSP.2011.942471 ↗
10. No reference image quality assessment metric via multi-domain structural information and piecewise regression10.1016/j.jvcir.2015.08.009 ↗
11. No reference quality assessment for multiply-distorted images based on an improved bag-of-words model10.1109/LSP.2015.2436908 ↗
12. No-reference image sharpness assessment based on discrepancy measures of structural degradation10.1016/j.jvcir.2020.102861 ↗
13. Highly efficient acoustic absorber designed by backing cavity-like and filled-microperforated plate-like structure10.1016/j.matdes.2022.111484 ↗
14. Quality assessment on remote sensing image based on neural networks10.1016/j.jvcir.2019.102580 ↗
15. A no-reference objective image sharpness metric for perception and estimation
16. A no-reference objective image sharpness metric based on the notion of just noticeable blur (JNB)10.1109/TIP.2008.2011760 ↗
17. No-reference image sharpness assessment via difference quotients10.1117/1.JEI.28.1.013032 ↗
18. Perceptual image quality assessment: A survey10.1007/s11432-019-2757-1 ↗
19. No-reference image quality assessment in the spatial domain10.1109/TIP.2012.2214050 ↗
20. No-reference quality assessment for multiply-distorted images in gradient domain10.1109/LSP.2016.2537321 ↗
21. Bovik, A.C., and Liu, S. (2001, January 7–11). DCT-domain blind measurement of blocking artifacts in DCT-coded images. Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing, Salt Lake City, UT, USA.
22. Blind image quality assessment via deep learning10.1109/TNNLS.2014.2336852 ↗
23. Objective quality assessment of image retargeting by incorporating fidelity measures and inconsistency detection10.1109/TIP.2017.2746260 ↗
24. An efficient image quality criterion in spatial domain
25. A no-reference image blurriness metric in the spatial domain10.1016/j.ijleo.2016.03.077 ↗
26. A perceptual image sharpness metric based on local edge gradient analysis10.1109/LSP.2013.2248711 ↗
27. Multidirectional gradient neighbourhood-weighted image sharpness evaluation algorithm
28. Objective quality evaluation of dehazed images10.1109/TITS.2018.2868771 ↗
29. Wang, F., Chen, J., Zhong, H.N., Ai, Y.B., and Zhang, W.D. (2022). No-Reference image quality assessment based on image multi-scale contour prediction. Appl. Sci., 12.10.3390/app12062833 ↗
30. Research on Vickers hardness image definition evaluation function10.4028/www.scientific.net/AMR.129-131.134 ↗
31. Autofocus method for SAR image with multi-blocks10.1049/joe.2019.0463 ↗
32. Quantum image sharpness estimation based on the Laplacian operator10.1142/S0219749920500082 ↗
33. Augmenting ADS-B with traffic information service-broadcast10.1109/MAES.2003.1244770 ↗
34. No-Reference image sharpness assessment based on maximum gradient and variability of gradients10.1109/TMM.2017.2780770 ↗
35. No-reference image blur assessment based on discrete orthogonal moments10.1109/TCYB.2015.2392129 ↗
36. Improving texture analysis performance in biometrics by adjusting image sharpness10.1016/j.patcog.2016.11.025 ↗
37. Survey of image edge detection10.3389/frsip.2022.826967 ↗
38. Effective and fast estimation for image sensor noise via constrained weighted least squares10.1109/TIP.2018.2812083 ↗
39. Edge detection algorithm of medical image based on Canny operator10.1088/1742-6596/1955/1/012080 ↗
40. Medical image enhancement based on Laplace transform, Sobel operator and Histogram equalization
41. Edge detection on noisy images using Prewitt operator and fractional order differentiation10.1007/s11042-022-12011-1 ↗
42. Perceptual blur and ringing metrics: Application to JPEG200010.1016/j.image.2003.08.003 ↗
43. DSPI filtering evaluation method based on Sobel operator and image entropy10.1109/JPHOT.2021.3118924 ↗
44. Liu, Z.Y., Hong, H.J., Gan, Z.H., Wang, J.H., and Chen, Y.P. (2022). An improved method for evaluating image sharpness based on edge information. Appl. Sci., 12.10.3390/app12136712 ↗
45. Improved faster R-CNN for fabric defect detection based on Gabor filter with genetic algorithm optimization10.1016/j.compind.2021.103551 ↗
46. A fast approach for no-reference image sharpness assessment based on maximum local variation10.1109/LSP.2014.2314487 ↗
47. No-reference image sharpness assessment in autoregressive parameter space10.1109/TIP.2015.2439035 ↗
48. Perceptual image quality assessment by independent feature detector10.1016/j.neucom.2014.04.081 ↗
49. A no-reference image blur metric based on the cumulative probability of blur detection (CPBD)10.1109/TIP.2011.2131660 ↗
50. A novel scheme for image sharpness using inflection points10.1002/ima.22415 ↗
51. Blind quality metric for multidistortion images based on cartoon and texture decomposition10.1109/LSP.2016.2594166 ↗
52. Deep image compression with lifting scheme: Wavelet transform domain based on high-frequency subband prediction10.1002/int.22769 ↗
53. Marichal, X., Ma, W.Y., and Zhang, H. (1999, January 24–28). Blur determination in the compressed domain using DCT information. Proceedings of the IEEE International Conference on Image Processing, Kobe, Japan.10.1109/ICIP.1999.822923 ↗
54. Multi-modal image sharpening in fourier transform infrared (FTIR) microscopy10.1039/D1AN00103E ↗
55. No-reference stereoscopic image quality assessment using quaternion wavelet transform and heterogeneous ensemble learning10.1016/j.displa.2021.102058 ↗
56. Pan, D., Shi, P., Hou, M., Ying, Z., Fu, S., and Zhang, Y. (2018, January 18–23). Blind predicting similar quality map for image quality assessment. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.10.1109/CVPR.2018.00667 ↗
57. No-reference quality assessment of JPEG images via a quality relevance map10.1109/LSP.2013.2296038 ↗
58. Image sharpness measure for blurred images in frequency domain10.1016/j.proeng.2013.09.086 ↗
59. No-reference image sharpness measure using discrete cosine transform statistics and multivariate adaptive regression splines for robotic applications10.1016/j.procs.2018.07.033 ↗
60. DCT-QM: A DCT-based quality degradation metric for image quality optimization problems10.1109/TIP.2016.2598492 ↗
61. A novel image quality assessment with globally and locally consilient visual quality perception10.1109/TIP.2016.2545863 ↗
62. DFT-based no-reference quality assessment of blurred images10.1007/s11042-022-11992-3 ↗
63. A no reference quality metric for measuring image blur in wavelet domain
64. A fast wavelet-based algorithm for global and local image sharpness estimation10.1109/LSP.2012.2199980 ↗
65. Image sharpness assessment based on local phase coherence10.1109/TIP.2013.2251643 ↗
66. Blind image sharpness assessment based on local contrast map statistics10.1016/j.jvcir.2017.11.017 ↗
67. Deep neural networks for no-reference and full-reference image quality assessment10.1109/TIP.2017.2760518 ↗
68. Burges, C., Shaked, T., and Renshaw, E. (2005, January 7). Learning to rank using gradient descent. Proceedings of the International Conference on Machine Learning, New York, NY, USA.10.1145/1102351.1102363 ↗
69. Ye, P., Kumar, J., and Kang, L. (2012, January 16–21). Unsupervised feature learning framework for no-reference image quality assessment. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Providence, RI, USA.
70. A No-Reference image sharpness metric based on large-scale structure10.1088/1742-6596/960/1/012018 ↗
71. Blind image blur metric based on orientation-aware local patterns10.1016/j.image.2019.115654 ↗
72. A two-step framework for constructing blind image quality indices10.1109/LSP.2010.2043888 ↗
73. Deep CNN-based blind image quality predictor10.1109/TNNLS.2018.2829819 ↗
74. Image quality assessment based on deep learning with FPGA implementation10.1016/j.image.2020.115780 ↗
75. Li, D.Q., Jiang, T.T., and Jiang, M. (2017, January 23–27). Exploiting high-level semantics for no-reference image quality assessment of realistic blur images. Proceedings of the 25th ACM International Conference on Multimedia, Mountain View, CA, USA.10.1145/3123266.3123322 ↗
76. Lin, K.Y., and Wang, G.X. (2018, January 18–23). Hallucinated-IQA: No-reference image quality assessment via adversarial learning. Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Salt Lake City, UT, USA.10.1109/CVPR.2018.00083 ↗
77. Blind image quality assessment using a deep bilinear convolutional neural network10.1109/TCSVT.2018.2886771 ↗
78. On the use of deep learning for blind image quality assessment10.1007/s11760-017-1166-8 ↗
79. Blind image quality prediction by exploiting multi-level deep representations10.1016/j.patcog.2018.04.016 ↗
80. Image sharpness assessment by sparse representation10.1109/TMM.2016.2545398 ↗
81. A no-reference image sharpness metric based on structural information using sparse representation10.1016/j.ins.2016.06.042 ↗
82. Blind image quality assessment based on high order statistics aggregation10.1109/TIP.2016.2585880 ↗
83. Optimizing multistage discriminative dictionaries for blind image quality assessment10.1109/TMM.2017.2763321 ↗
84. Blind image quality assessment using local consistency aware retriever and uncertainty aware evaluator10.1109/TCSVT.2017.2710419 ↗
85. Content-insensitive blind image blurriness assessment using Weibull statistics and sparse extreme learning machine10.1109/TSMC.2017.2718180 ↗
86. Zhang, Y.B., Wang, H.Q., Tan, F.F., Chen, W.J., and Wu, Z.R. (2019, January 22–25). No-reference image sharpness assessment based on rank learning. Proceedings of the 2019 International Conference on Image Processing (ICIP), Taipei, Taiwan.10.1109/ICIP.2019.8803370 ↗
87. Image quality assessment based on adaptive multiple Skyline query10.1016/j.image.2019.115676 ↗
88. S3: A spectral and spatial measure of local perceived sharpness in natural image10.1109/TIP.2011.2169974 ↗
89. Quality assessment for inspection images of power lines based on spatial and sharpness evaluation10.1049/ipr2.12352 ↗
90. Combining local and global measures for DIBR-Synthesized image quality evaluation10.1109/TIP.2018.2875913 ↗
91. Zhang, S., Li, P., Xu, X.H., Li, L., and Chang, C.C. (2018). No-reference image blur assessment based on response function of singular values. Symmetry, 10.10.3390/sym10080304 ↗
92. A structural variation classification model for image quality assessment10.1109/TMM.2017.2689923 ↗
93. Which has better visual quality: The clear blue sky or a blurry animal?10.1109/TMM.2018.2875354 ↗
94. No-reference image quality assessment with shearlet transform and deep neural networks10.1016/j.neucom.2014.12.015 ↗
95. A statistical evaluation of recent full reference image quality assessment algorithms10.1109/TIP.2006.881959 ↗
96. Most apparent distortion: Full-reference image quality assessment and the role of strategy10.1117/1.3267105 ↗
97. TID2008-a database for evaluation of full-reference visual quality assessment metrics
98. Ponomarenko, N., Ieremeiev, O., and Lukin, V. (2013, January 10–12). Color image database TID2013: Peculiarities and preliminary results. Proceedings of the European Workshop on Visual Information Processing (EUVIP), Paris, France.
99. No-reference blur assessment of digital pictures based on multifeature classifiers10.1109/TIP.2010.2053549 ↗
100. CID2013: A database for evaluating no-reference image quality assessment algorithms10.1109/TIP.2014.2378061 ↗