pith. sign in

arxiv: 1906.08673 · v1 · pith:KBVQ3JBFnew · submitted 2019-06-19 · 📡 eess.IV · cs.MM

Enhancement of Underwater Images with Statistical Model of Background Light and Optimization of Transmission Map

Wei Song , Yan Wang , Dongmei Huang , Antonio Liotta , Cristian Perra This is my paper

Pith reviewed 2026-05-25 20:10 UTC · model grok-4.3

classification 📡 eess.IV cs.MM
keywords underwater image enhancementbackground light estimationtransmission mapimage restorationcolor correctionstatistical modeldark channel prior
0
0 comments X

The pith

Statistical models from manually annotated background lights enable more accurate and faster restoration of underwater images than prior methods.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper builds a database of manually annotated background lights to derive statistical models that estimate background light from image histograms. It estimates a coarse transmission map for the red channel using an underwater dark channel prior, then refines it with a scene depth map and reversed saturation map before deriving green and blue channel maps from attenuation differences. Color correction via adjusted white balance is applied last to improve natural appearance. A sympathetic reader would care because underwater images suffer from absorption and scattering that degrade quality for marine observation and robotics, and better parameter estimation could yield clearer results with less processing effort.

Core claim

The method combines statistical background light estimation from an MABLs database, refined transmission maps based on underwater dark channel prior and light attenuation, and post-processing color correction to restore underwater images, achieving higher accuracy in background light estimates, reduced computation time, superior visual performance, and greater information retention compared to state-of-the-art approaches.

What carries the argument

Robust statistical models of background light estimation derived from the relationship between manually annotated background lights and histogram distributions of underwater images, paired with adjusted transmission map computation via underwater dark channel prior.

If this is right

  • More accurate background light estimates produce restored images with fewer artifacts from scattering and absorption.
  • Lower computation time supports deployment in real-time underwater imaging systems.
  • Superior performance metrics translate to enhanced visibility for tasks like object detection in marine environments.
  • Greater retention of valuable information preserves details useful for scientific analysis of underwater scenes.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • The annotation-based modeling approach could be adapted to other scattering media such as fog if similar labeled databases are built for those domains.
  • Integration with downstream computer vision pipelines might improve detection rates in turbid water without additional hardware.
  • Varying the water type distributions in the training database could test how well the statistical models generalize across different ocean conditions.

Load-bearing premise

The relationship between manually annotated background lights and the histogram distributions of various underwater images yields robust statistical models of background light estimation.

What would settle it

Running the statistical models on a new set of underwater images with independently annotated ground-truth background lights and finding that the estimates are less accurate or slower than competing methods on standard quality metrics.

Figures

Figures reproduced from arXiv: 1906.08673 by Antonio Liotta, Cristian Perra, Dongmei Huang, Wei Song, Yan Wang.

Figure 1
Figure 1. Figure 1 [PITH_FULL_IMAGE:figures/full_fig_p004_1.png] view at source ↗
Figure 13
Figure 13. Figure 13: (a) Accuracy of the estimated BLs in the reference with MABLs. (b) The running times (/s) with different sizes (/pixels) of test underwater images. The overall performance of our statistical model of BLs estimation can be seen in [PITH_FULL_IMAGE:figures/full_fig_p012_13.png] view at source ↗
Figure 14
Figure 14. Figure 14: Comparisons results with different color tones based on different BLs and the same TM. (a) Input images. (b)-(i) Restored results with different BLs proposed by (b) DCP, (c) MIP, (d) UDCP, (e) Li, (f) Peng, (g) Ours, (h) MABLs. D. Performance of TM Optimizer Since the above experimental results have adequately demonstrated that the MABLs are best suitable to diverse underwater image restoration, we examin… view at source ↗
Figure 15
Figure 15. Figure 15: Comparison results restored with different TMs based on the MABLs. (a) Original images. The restored results by (b) DCP, (c) MIP, (d) UDCP, (e) Peng, (f) Ours. From the full-reference and non-reference quality analysis in Table III, the results of DCP, MIP and UDCP methods are extraordinary lower than the results of our method and Peng’s. Although the results of Peng’s method have a little better than the… view at source ↗
Figure 16
Figure 16. Figure 16: shows two examples of the comparison results. From Table IV, we can see that adding HE to the methods of DCP, MIP, UDCP and Peng brings significant improvement of quality assessment at the cost of a slightly increase of running time. The last row of RT (s) in Table IV presents the average running time of the images with 400×600 pixels processed by our method. Based on experiments, the running time of the … view at source ↗
Figure 18
Figure 18. Figure 18: Comparison results. (a) Original images, (b) Ding’s method [37], (c) Ours. VI. CONCLUSION We have proposed an underwater image enhancement method including underwater image restoration based on novel statistical models of BLs estimation and optimal TM estimation models, and a simple color correction based on improved white balance, in accordance with the characteristics of the underwater images. To guaran… view at source ↗
read the original abstract

Underwater images often have severe quality degradation and distortion due to light absorption and scattering in the water medium. A hazed image formation model is widely used to restore the image quality. It depends on two optical parameters: the background light and the transmission map. Underwater images can also be enhanced by color and contrast correction from the perspective of image processing. In this paper, we propose an effective underwater image enhancement method for underwater images in composition of underwater image restoration and color correction. Firstly, a manually annotated background lights (MABLs) database is developed. With reference to the relationship between MABLs and the histogram distributions of various underwater images, robust statistical models of BLs estimation are provided. Next, the TM of R channel is roughly estimated based on the new underwater dark channel prior via the statistic of clear and high resolution underwater images, then a scene depth map based on the underwater light attenuation prior and an adjusted reversed saturation map are applied to compensate and modify the coarse TM of R channel. Next, TMs of G-B channels are estimated based on the difference of attenuation ratios between R channel and G-B channels. Finally, to improve the color and contrast of the restored image with a natural appearance, a variation of white balance is introduced as post-processing. In order to guide the priority of underwater image enhancement, sufficient evaluations are conducted to discuss the impacts of the key parameters including BL and TM, and the importance of the color correction. Comparisons with other state-of-the-art methods demonstrate that our proposed underwater image enhancement method can achieve higher accuracy of estimated BLs, less computation time, more superior performance, and more valuable information retention.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

3 major / 2 minor

Summary. The paper claims to develop a manually annotated background lights (MABLs) database from which statistical models for background light (BL) estimation are derived based on histogram distributions; it then estimates the transmission map (TM) of the R channel via a new underwater dark channel prior from clear-image statistics, compensates it using a scene depth map from the underwater light attenuation prior and an adjusted reversed saturation map, derives G/B-channel TMs from attenuation-ratio differences, and applies a white-balance variant as post-processing. The central claims are higher accuracy of estimated BLs, reduced computation time, superior performance, and greater information retention relative to prior state-of-the-art methods.

Significance. If the statistical models generalize and the reported accuracy is shown to be independent of the fitting data, the MABLs database and associated models would constitute a useful data-driven contribution to underwater image restoration, addressing failures of conventional priors. The explicit discussion of parameter impacts and the role of color correction is also a constructive element.

major comments (3)
  1. [MABLs Database and Statistical Models of BL Estimation] The claim of higher accuracy of estimated BLs is load-bearing for the central contribution, yet the statistical models are derived from the MABLs database and accuracy is measured against those same annotations. The manuscript provides no description of a held-out test partition, cross-validation procedure, database size, or annotation protocol, leaving open whether the superiority is an independent test or an in-sample fit.
  2. [Comparisons with other state-of-the-art methods] The abstract asserts superior performance and information retention over other methods, but supplies no quantitative tables, error bars, ablation studies, or details on the composition of the evaluation set. If the full manuscript likewise lacks these, the robustness of the performance claims cannot be verified.
  3. [TM Estimation] The TM of the R channel is first estimated from the underwater dark channel prior and then modified by a scene depth map and adjusted reversed saturation map. The precise equations governing these compensation steps and the selection of any free parameters (including attenuation-ratio differences) are not shown to be independent of the evaluation data, undermining the reproducibility of the reported gains.
minor comments (2)
  1. [Abstract] The abstract is a single dense paragraph; breaking the method description into enumerated steps would improve readability.
  2. [Throughout] Ensure that all acronyms (BL, TM, MABLs) are defined on first use and used consistently in figure captions and tables.

Simulated Author's Rebuttal

3 responses · 0 unresolved

We thank the referee for the constructive feedback and the recommendation for major revision. We address each major comment below, agreeing where clarifications are needed and committing to revisions that strengthen the manuscript without misrepresenting our work.

read point-by-point responses

  1. Referee: [MABLs Database and Statistical Models of BL Estimation] The claim of higher accuracy of estimated BLs is load-bearing for the central contribution, yet the statistical models are derived from the MABLs database and accuracy is measured against those same annotations. The manuscript provides no description of a held-out test partition, cross-validation procedure, database size, or annotation protocol, leaving open whether the superiority is an independent test or an in-sample fit.

    Authors: We agree that the manuscript does not provide sufficient details on database construction and validation. The MABLs database was created by manual annotation of background lights in underwater images, with statistical models derived from observed histogram distributions. Accuracy was assessed via direct comparison to these annotations. In the revision, we will add the database size, a description of the annotation protocol, and results from a held-out test partition (or cross-validation) to demonstrate generalization independent of the fitting data. revision: yes

  2. Referee: [Comparisons with other state-of-the-art methods] The abstract asserts superior performance and information retention over other methods, but supplies no quantitative tables, error bars, ablation studies, or details on the composition of the evaluation set. If the full manuscript likewise lacks these, the robustness of the performance claims cannot be verified.

    Authors: The manuscript contains comparisons with prior methods, including metrics on accuracy, speed, and information retention across test images. However, we acknowledge that more detailed quantitative support is warranted. The revision will incorporate explicit tables with numerical results, error bars across the evaluation set, ablation studies on components such as BL estimation and TM compensation, and a full description of the test image composition and selection criteria. revision: yes

  3. Referee: [TM Estimation] The TM of the R channel is first estimated from the underwater dark channel prior and then modified by a scene depth map and adjusted reversed saturation map. The precise equations governing these compensation steps and the selection of any free parameters (including attenuation-ratio differences) are not shown to be independent of the evaluation data, undermining the reproducibility of the reported gains.

    Authors: The manuscript details the initial TM estimation via the underwater dark channel prior (derived from clear-image statistics) and subsequent compensation steps using the scene depth map and adjusted reversed saturation map, with G/B-channel TMs obtained from attenuation-ratio differences. These ratios draw from established underwater light attenuation properties rather than per-image tuning. In revision, we will present all governing equations explicitly, specify the fixed parameter values and their physical basis, and confirm they are independent of the evaluation images to ensure full reproducibility. revision: yes

Circularity Check

0 steps flagged

No significant circularity in derivation chain

full rationale

The paper develops an MABLs database and derives statistical models of background light from the observed relationship to histogram distributions of underwater images. This is a standard data-driven modeling step. The abstract claims higher accuracy of estimated BLs via comparisons, but provides no equations, no explicit statement that test images overlap the fitting set without cross-validation, and no reduction of any claimed prediction to the input annotations by construction. No self-citation load-bearing, no ansatz smuggling, and no fitted parameter renamed as independent prediction appear in the given text. The central method is therefore self-contained against its own described inputs.

Axiom & Free-Parameter Ledger

2 free parameters · 2 axioms · 0 invented entities

The method rests on the standard hazed image formation model, the validity of the dark channel prior for underwater scenes, and the assumption that histogram statistics reliably predict background light; no new physical entities are postulated.

free parameters (2)
  • statistical model parameters for BL estimation
    Parameters in the robust statistical models linking MABLs to histogram distributions are fitted from the new database.
  • attenuation ratio differences between channels
    Differences used to derive G-B transmission maps from the R-channel map are taken from prior literature but may require tuning.
axioms (2)
  • domain assumption The hazed image formation model applies to underwater images
    Stated as widely used and adopted without new derivation.
  • domain assumption Clear high-resolution underwater images provide a reliable statistic for the new underwater dark channel prior
    Invoked to estimate the coarse TM of the R channel.

pith-pipeline@v0.9.0 · 5838 in / 1344 out tokens · 29846 ms · 2026-05-25T20:10:19.004272+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Lean theorems connected to this paper

Citations machine-checked in the Pith Canon. Every link opens the source theorem in the public Lean library.

What do these tags mean?
matches
The paper's claim is directly supported by a theorem in the formal canon.
supports
The theorem supports part of the paper's argument, but the paper may add assumptions or extra steps.
extends
The paper goes beyond the formal theorem; the theorem is a base layer rather than the whole result.
uses
The paper appears to rely on the theorem as machinery.
contradicts
The paper's claim conflicts with a theorem or certificate in the canon.
unclear
Pith found a possible connection, but the passage is too broad, indirect, or ambiguous to say the theorem truly supports the claim.

Reference graph

Works this paper leans on

43 extracted references · 43 canonical work pages

  1. [1]

    Efficient No -Reference Quality Assessment and Classification Model for Contrast Distorted Images,

    H. Ziaei Nafchi and M. Cheriet, “Efficient No -Reference Quality Assessment and Classification Model for Contrast Distorted Images,” IEEE Trans. Broadcast., vol. 64, no. 2, pp. 518–523, Jun. 2018

    work page 2018

  2. [2]

    Self-Tuning Underwater Image Restoration,

    E. Trucco and A. T. Olmos -Antillon, “Self-Tuning Underwater Image Restoration,” IEEE J. Ocean. Eng. , vol. 31, no. 2, pp. 511 –519, Apr. 2006

    work page 2006

  3. [3]

    Blind Image Quality Estimation via Distortion Aggravation,

    X. Min, G. Zhai, K. Gu, Y. Liu, and X. Yang, “Blind Image Quality Estimation via Distortion Aggravation,” IEEE Trans. Broadcast., vol. 64, no. 2, pp. 508–517, Jun. 2018

    work page 2018

  4. [4]

    A Computer Model For Underwater Camera Systems,

    B. L. McGlamery, “A Computer Model For Underwater Camera Systems,” presented at the Ocean Optics VI, 1980, vol. 0208, pp. 221– 232

    work page 1980

  5. [5]

    Computer modeling and the design of optimal underwater imaging systems,

    J. S. Jaffe, “Computer modeling and the design of optimal underwater imaging systems,” IEEE J. Ocean. Eng., vol. 15, no. 2, pp. 101 –111, Apr. 1990

    work page 1990

  6. [6]

    Underwater Image Processing: State of the Art of Restoration and Image Enhancement Methods,

    R. Schettini and S. Corchs, “Underwater Image Processing: State of the Art of Restoration and Image Enhancement Methods,” EURASIP J. Adv. Signal Process., vol. 2010, no. 1, p. 746052, Apr. 2010

    work page 2010

  7. [7]

    Contrast limited adaptive histogram equalization,

    K. Zuiderveld, “Contrast limited adaptive histogram equalization,” P. S. Heckbert, Ed. San Diego, CA, USA: Academic Press Professional, Inc., 1994, pp. 474–485

    work page 1994

  8. [8]

    Mixture contrast limit ed adaptive histogram equalization for underwater image enhancement,

    M. S. Hitam, E. A. Awalludin, W. N. J. H. W. Yussof, and Z. Bachok, “Mixture contrast limit ed adaptive histogram equalization for underwater image enhancement,” in 2013 International Conference on Computer Applications Technology (ICCAT), 2013, pp. 1–5

    work page 2013

  9. [9]

    Underwater Image Enhancement Using An Integrated Colour Model.,

    K. Iqbal, R. Abdul Salam, M. A. Osman, and A. Z. Talib, “Underwater Image Enhancement Using An Integrated Colour Model.,” IAENG Int. J. Comput. Sci., vol. 32, no. 2, pp. 239–244, 2007

    work page 2007

  10. [10]

    Enhancing the low quality images using Unsupervised Colour Correction Method,

    K. Iqbal, M. Odetayo, A. James, R. A. Salam, and U. O. I. P. a C. R. Talib, “Enhancing the low quality images using Unsupervised Colour Correction Method,” in 2010 IEEE International Conference on Systems, Man and Cybernetics, 2010, pp. 1703–1709

    work page 2010

  11. [11]

    Enhancing underwater images and videos by fusion,

    C. Ancuti, C. O. Ancuti, T. Haber, and P. Bekaert, “Enhancing underwater images and videos by fusion,” in 2012 IEEE Conference on Computer Vision and Pattern Recognition, 2012, pp. 81–88

    work page 2012

  12. [12]

    Underwater image quality enhancement through integrated color model with Rayleigh distribution,

    A. S. A. Ghani and N. A. M. Isa, “Underwater image quality enhancement through integrated color model with Rayleigh distribution,” Appl. Soft Comput., vol. 27, pp. 219–230, Feb. 2015

    work page 2015

  13. [13]

    Underwater image quality enhancement through composition of dual -intensity images and Rayleigh-stretching,

    A. S. A. Ghani and N. A. M. Isa, “Underwater image quality enhancement through composition of dual -intensity images and Rayleigh-stretching,” SpringerPlus, vol. 3, no. 1, p. 757, Dec. 2014

    work page 2014

  14. [14]

    Automatic system for improving underwater image contras t and color through recursive adaptive histogram modification,

    A. S. Abdul Ghani and N. A. Mat Isa, “Automatic system for improving underwater image contras t and color through recursive adaptive histogram modification,” Comput. Electron. Agric. , vol. 141, no. Supplement C, pp. 181–195, Sep. 2017

    work page 2017

  15. [15]

    Single Image Haze Removal Using Dark Channel Prior,

    K. He, J. Sun, and X. Tang, “Single Image Haze Removal Using Dark Channel Prior,” IEEE Trans. Pattern Anal. M ach. Intell., vol. 33, no. 12, pp. 2341–2353, Dec. 2011

    work page 2011

  16. [16]

    Removal of water scattering,

    L. Chao and M. Wang, “Removal of water scattering,” in 2010 2nd International Conference on Computer Engineering and Technology , 2010, vol. 2, pp. V2-35-V2-39

    work page 2010

  17. [17]

    Underwater Image Enhancement by Wavelength Compensation and Dehazing,

    J. Y. Chiang and Y. C. Chen, “Underwater Image Enhancement by Wavelength Compensation and Dehazing,” IEEE Trans. Image Process., vol. 21, no. 4, pp. 1756–1769, Apr. 2012

    work page 2012

  18. [18]

    Transmission Estimation in Underwater Single Images,

    P. Drews, E. Nascimento, F. Moraes, S. Botelho, and M. Campos, “Transmission Estimation in Underwater Single Images,” presented at the Proceedings of the IEEE International Conference on Computer Vision Workshops, 2013, pp. 825–830

    work page 2013

  19. [19]

    Underwater Depth Estimation and Image Restoration Based on Single Images,

    P. L. J. Drews, E. R. Nascimento, S. S. C. Botelho, and M. F. M. Campos, “Underwater Depth Estimation and Image Restoration Based on Single Images,” IEEE Comput. Graph. Appl., vol. 36, no. 2, pp. 24– 35, Mar. 2016

    work page 2016

  20. [20]

    Automatic Red- Channel underwater image restoration,

    A. Galdran, D. Pardo, A. Picó n, and A. Alvarez-Gila, “Automatic Red- Channel underwater image restoration,” J. Vis. Commun. Image Represent., vol. 26, pp. 132–145, Jan. 2015

    work page 2015

  21. [21]

    Single underwater image restoration by blue-green channels dehazing and red channel correction,

    C. Li, J. Quo, Y. Pang, S. Chen, and J. Wang, “Single underwater image restoration by blue-green channels dehazing and red channel correction,” in 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2016, pp. 1731–1735

    work page 2016

  22. [22]

    Single underwater image enhancement using depth estimation based on blurriness,

    Y. T. Peng, X. Zhao, and P. C. Cosman, “Single underwater image enhancement using depth estimation based on blurriness,” in 2015 IEEE International Conference on Image Processing (ICIP), 2015, pp. 4952–4956

    work page 2015

  23. [23]

    Underwater Image Restoration Based on Image Blurriness and Light Absorption,

    Y. T. Peng and P. C. Co sman, “Underwater Image Restoration Based on Image Blurriness and Light Absorption,” IEEE Trans. Image Process., vol. 26, no. 4, pp. 1579–1594, Apr. 2017

    work page 2017

  24. [24]

    Initial results in underwater single image d ehazing,

    N. Carlevaris-Bianco, A. Mohan, and R. M. Eustice, “Initial results in underwater single image d ehazing,” in OCEANS 2010 MTS/IEEE SEATTLE, 2010, pp. 1–8

    work page 2010

  25. [25]

    Underwater image colour constancy based on DSNMF,

    X. Liu, G. Zhong, C. Liu, and J. Dong, “Underwater image colour constancy based on DSNMF,” IET Image Process., vol. 11, no. 1, pp. 38–43, 2017

    work page 2017

  26. [26]

    Unde rwater image dehaze using scene depth estimation with adaptive color correction,

    X. Ding, Y. Wang, J. Zhang, and X. Fu, “Unde rwater image dehaze using scene depth estimation with adaptive color correction,” in OCEANS 2017 - Aberdeen, 2017, pp. 1–5

    work page 2017

  27. [27]

    Underwater Image Restoration using Deep Networks to Estimate Background Light and Scene Depth,

    K. Cao, Y.-T. Peng, and P. C. Cosman, “Underwater Image Restoration using Deep Networks to Estimate Background Light and Scene Depth,” p. 4

    work page

  28. [28]

    Depth Map Prediction from a Single Image using a Multi-Scale Deep Network,

    D. Eigen, C. Puhrsch, and R. Fergus, “Depth Map Prediction from a Single Image using a Multi-Scale Deep Network,” p. 9

    work page

  29. [29]

    Chromatic framework for vision in bad weather,

    S. G. Narasimhan and S. K. Nayar, “Chromatic framework for vision in bad weather,” in Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662), 2000, vol. 1, pp. 598–605 vol.1

    work page 2000

  30. [30]

    Single Image Dehazing,

    R. Fattal, “Single Image Dehazing,” in ACM SIGGRAPH 2008 Papers, New York, NY, USA, 2008, pp. 72:1–72:9

    work page 2008

  31. [31]

    Vision and the Atmosphere,

    S. G. Narasimhan and S. K. Nayar, “Vision and the Atmosphere,” Int. J. Comput. Vis., vol. 48, no. 3, pp. 233–254, Jul. 2002

    work page 2002

  32. [32]

    Visibility in bad weather from a single image,

    R. T. Tan, “Visibility in bad weather from a single image,” in 2008 IEEE Conference on Computer Vision and Pattern Recognition, 2008, pp. 1–8

    work page 2008

  33. [33]

    Deriving inherent optical properties from background color and underwater image enhancement,

    X. Zhao, T. Jin, and S. Qu, “Deriving inherent optical properties from background color and underwater image enhancement,” Ocean Eng., vol. 94, pp. 163–172, Jan. 2015

    work page 2015

  34. [34]

    Low Complexity Underwater Image Enhancement Based on Dark Channel Prior,

    H. Y. Yang, P. Y. Chen, C. C. Huang, Y. Z. Zhuang, and Y. H. Shiau, “Low Complexity Underwater Image Enhancement Based on Dark Channel Prior,” in 2011 Second International Conference on Innovations in Bio-inspired Computing and Applications, 2011, pp. 17– 20

    work page 2011

  35. [35]

    Underwater Image Enhancement by Dehazing With Minimum Information Loss and Histogram Distribution Prior,

    C. Y. Li, J. C. Guo, R. M. Cong, Y. W. Pang, and B. W ang, “Underwater Image Enhancement by Dehazing With Minimum Information Loss and Histogram Distribution Prior,” IEEE Trans. Image Process., vol. 25, no. 12, pp. 5664–5677, Dec. 2016

    work page 2016

  36. [36]

    Light in the Sea*,

    S. Q. Duntley, “Light in the Sea*,” JOSA, vol. 53, no. 2, pp. 214–233, Feb. 1963

    work page 1963

  37. [37]

    Single underwater image enhancement with a new optical model,

    H. Wen, Y. Tian, T. Huang, and W. Gao, “Single underwater image enhancement with a new optical model,” in 2013 IEEE International Symposium on Circuits and Systems (ISCAS2013), 2013, pp. 753–756

    work page 2013

  38. [38]

    Shallow-Water Image Enhancement Using Relative Global Histogram Stretching Based on Adaptive Parameter Acquisition,

    D. Huang, Y. Wang, W. Song, J. Seque ira, and S. Mavromatis, “Shallow-Water Image Enhancement Using Relative Global Histogram Stretching Based on Adaptive Parameter Acquisition,” in MultiMedia Modeling, 2018, pp. 453–465. 17

    work page 2018

  39. [39]

    Guided Image Filtering,

    K. He, J. Sun, and X. Tang, “Guided Image Filtering,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 35, no. 6, pp. 1397–1409, Jun. 2013

    work page 2013

  40. [40]

    Shades of Gray and Colour Constancy,

    G. D. Finlayson and E. Trezzi, “Shades of Gray and Colour Constancy,” Color Imaging Conf., vol. 2004, no. 1, pp. 37–41, Jan. 2004

    work page 2004

  41. [41]

    Image quality assessment: from error visibility to structural similarity,

    Z. Wang, A. C. Bovik, H. R. Sheikh, and E. P . Simoncelli, “Image quality assessment: from error visibility to structural similarity,” IEEE Trans. Image Process., vol. 13, no. 4, pp. 600–612, Apr. 2004

    work page 2004

  42. [42]

    No -Reference Image Quality Assessment in the Spat ial Domain,

    A. Mittal, A. K. Moorthy, and A. C. Bovik, “No -Reference Image Quality Assessment in the Spat ial Domain,” IEEE Trans. Image Process., vol. 21, no. 12, pp. 4695–4708, Dec. 2012

    work page 2012

  43. [43]

    An Underwater Color Image Quality Evaluation Metric,

    M. Yang and A. Sowmya, “An Underwater Color Image Quality Evaluation Metric,” IEEE Trans. Image Process. , vol. 24, no. 12, pp. 6062–6071, Dec. 2015

    work page 2015