645

3C Tecnología. Glosas de innovación aplicadas a la pyme. ISSN: 2254 – 4143 Edición Especial Special Issue

Noviembre 2021

HYBRID TECHNIQUE FOR IMPROVING UNDERWATER

IMAGE

A. Chrispin Jiji

Assistant Professor, Department of Electronics and Communication Engineering,

The Oxford College of Engineering, Bangalore, (India).

E-mail: chrispinjij@gmail.com

ORCID: https://orcid.org/0000-0001-5267-788x

Nagaraj Ramrao

Vice Chancellor, Kalasalingam University, Srivilliputtur, Tamilnadu, (India).

E-mail: Nagaraj.ramrao@gmail.com

ORCID: https://orcid.org/0000-0003-2542-5999

Recepción:

29/11/2019

Aceptación:

12/11/2020

Publicación:

30/11/2021

Citación sugerida:

Jiji, A. C., y Ramrao, N. (2021). Hybrid technique for improving underwater image. 3C Tecnología.

Glosas de innovación aplicadas a la pyme, Edición Especial, (noviembre, 2021), 645-665. https://doi.

org/10.17993/3ctecno.2021.specialissue8.645-665

646

https://doi.org/10.17993/3ctecno.2021.specialissue8.645-665

3C Tecnología. Glosas de innovación aplicadas a la pyme. ISSN: 2254 – 4143 Edición Especial Special Issue

Noviembre 2021

ABSTRACT

As light attenuate when disseminating in water, descriptions conned beneath water is

generally corrupted towards varying degrees. An acquired image underneath water gets

degraded due to optical properties of light in water. First, we describe optical behaviour of

light in ocean due to which acquired images gets degraded. However, due to degradation

of observed picture, conventional forms are not correct enough for faithful reconstruction.

So, to improve the perception, we intend a Non-Locally Centralized Method (NLCM)

for deblurring underwater descriptions. Later by considering characteristic of light

propagation, we propose Gradient Guided Filter (GGF) method for improving the visibility

of picture details. Finally, the image is well enhanced by Hybrid technique called Non-

locally centralized gradient guided lter (NLCM-GGF). Tentative outcome demonstrates

that proposed technique produces improved results than several conventional techniques

together in quality metrics and visual evaluation.

KEYWORDS

Underwater Image Processing, Deblurring, Edge preserving lters.

647

https://doi.org/10.17993/3ctecno.2021.specialissue8.645-665

3C Tecnología. Glosas de innovación aplicadas a la pyme. ISSN: 2254 – 4143 Edición Especial Special Issue

Noviembre 2021

1. INTRODUCTION

Light always acts a signicant task in oceanic explorer. Light transmission in sea is the

base of ocular studies for describing light transmission procedure. Underwater image

analysis attracts an increased level of attention as well as support of ocean application

such as undersea exploration; see life in undersea, ocean rescue in Lebart et al. (2003) and

species identication in Strachan (1993). Thus, it has been a challenging task to restore

as well enhance underwater images reasons the variation in ocular property underneath.

The main eect of degradation processes causes turbid, decreases visibility along with

color distortion owing to ocular property. In particular, for severe absorption of light,

conned picture is under exposed. In the meantime, altered wavelength of light has diverse

absorbing characteristic in Seibert (1963), attained picture has cruel color distortion. Larger

wavelength determines poorer attenuation in transmission medium. Shorter wavelength

travel further, because of these undersea descriptions subject to blue or green color in

Torres-Méndez and Dudek (2005). The water turbidity in Huimin et al. (2015) and organic

element suspended on medium yields a hard restoration problem, since overall technique

becomes highly dependent on environmental conditions.

Numerous works encompass to undertake those problems. For past decades, an extensive

study has performed to build up a variety of reconstruction methods in Bertero and

Boccacci (1998), and Chan et al. (2005). Based on ill-posed nature, several methods are

widely employed to improve the restored picture. For eective process, it is very important to

model earlier facts of natural descriptions. The classic models, such as quadratic Tikhonov

as well as TV model in Oliveira, Bioucas-Dias, and Figueiredo (2009) are eective to

decrease noise artefacts however have a tendency to over-smooth the descriptions based on

piecewise steady statement. As a substitute, in modern era sparsity model in Daubechies,

Defrise, and De Mol (2004) and Dong et al. (2011) shows the potential outcome for dierent

reconstruction issues in Mairal, Elad, and Sapiro (2008) and Mairal et al. (2009).

In this paper, we intend hybrid technique for improving underwater image. Our

contributions are two-fold: (1) Non-Locally Centralized Method (NLCM) for deblurring

the images; (2) Gradient Guided Filter (GGF) method for enhancing the images. Finally,

the proposed NLCM-GGF method better improve its quality than conventional technique.

648

https://doi.org/10.17993/3ctecno.2021.specialissue8.645-665

3C Tecnología. Glosas de innovación aplicadas a la pyme. ISSN: 2254 – 4143 Edición Especial Special Issue

Noviembre 2021

Tentative result shows that projected technique performs better than many conventional

techniques together in quality metrics and visual evaluation. In the rest of the paper, we

present short outline of earlier art and describe optical properties of light under water

in section 2. Section 3 describes proposed hybrid technique. Section 4 describes tentative

result; nally, section 5 brings to a close note.

2. MATERIALS AND METHODS

A variety of techniques has projected for getting better ocular excellence of degraded

undersea descriptions, roughly classied into deblurring and enhancement process.

Deblurring undersea picture is an ill-posed problem. As an essential issue in undersea

description, reconstructions have widely considered in earlier years in Banham and

Katsag (1997) and Bioucas-Dias and Figueiredo (2007). The ill-posed nature of IR is

normally not exceptional. Past facts of typical descriptions employed to regularize such

issues in reconstruction. The main model is total variation (TV) which lack exibility

for characterizing local picture structures but often generates over-smoothed results. To

well keep up the picture boundaries, several methods have developed for improving TV

model in Lysaker and Tai (2006), Beck and Teboulle (2009) and Chantas et al. (2010). The

autoregressive (AR) modelling in Wu, Zhang, and Wang (2009) closely computes a primary

representation which gives improved results than TV model to restore boundary formation,

but have a tendency to generate ghost artefact.

In Buades, Coll, and Morel (2005) training-based adaptive scheme learns a better-quality

learning pictures, to increase its accuracy. In modern era non-local (NL) in Kindermann,

Osher, and Jones (2005) and Zhang et al. (2010) process has led a hopeful eect in several

reconstruction schemes. The plan of NL process is straightforward: patch that contain

related pattern be spatially distant and so we bring together in the image. In Dong et al.

(2011) and Jiji and Vivek (2017), the edges are sharper than all the other process but there

shows some ringing noise around edges and with dierent patches for reconstructing the

images in Jiji and Ramrao (2017). With this aim, centralized NL method exploits NL

redundancy to lower SCN noise.

649

https://doi.org/10.17993/3ctecno.2021.specialissue8.645-665

3C Tecnología. Glosas de innovación aplicadas a la pyme. ISSN: 2254 – 4143 Edición Especial Special Issue

Noviembre 2021

The NCSR method in Dong et al. (2013), use NL self-similarity for gaining ne approximation

of sparse code coecients, later integrate attained picture to those approximation. It is also

characterized by training online sub-dictionaries by choosing most excellent online sub-

dictionary for every patch. It employs Iterative Shrinkage-Threshold (IST) for solving l-norm

trouble produced by model. Although the method achieved good, but never considers the

statistical picture formation, therefore undergo artefact near boundaries.

Enhancement method does not rely on any picture formation, and enhances imagery by

modifying scene pixel values. In Farbman et al. (2008) ne points in true description will

smooth while keep boundaries to subtract smooth picture from true description for generating

detailed picture. The mixture of range and domain lter in Tomasi and Manduchi (1998)

keeps boundaries sharper, but experience gradient problems next to few boundaries. To

avoid gradient reversal artifacts in He, Sun, and Tang (2013), picture elements in a window

consider the structure of guidance image, but fail to signify close to a few boundaries. The

boundary responsive factor in Li et al. (2015) lowers halo artifact which makes the edges

better, but they cannot keep up edges well in some cases. The factors in Kou et al. (2015)

signify the descriptions more correctly next to boundaries and keep up good boundaries.

The work in Jiji and Ramrao (2019) is the extensive version primarily existed to improve

the undersea imagery.

Here, we describe a hybrid technique for improving undersea descriptions which built

upon the idea of NLCM exploit regulation limit determines the geometrical formation of

image. A new method is particularly functional on boundaries of restored representation,

so known as NLCM based Gradient guided lter (NLCM-GGF). Experimental results

proved that the projected scheme gives much enhancement in both quality metrics and

visual excellence than conventional technique.

2.1. OPTICAL PROPERTIES IN WATER

This section describes the behaviour of beam in undersea. Beam propagates in water medium

is same as in air. Absorption denotes power reduction and scattering refers to deection of

propagation path. In underwater environment, beam also undergoes diraction as well as

refraction due to its wavelength and refractive index of water. Lambert-Beer empirical law

states that the ocular property decay underneath material via exponential dependence:

650

https://doi.org/10.17993/3ctecno.2021.specialissue8.645-665

3C Tecnología. Glosas de innovación aplicadas a la pyme. ISSN: 2254 – 4143 Edición Especial Special Issue

Noviembre 2021

(1)

where c denotes overall attenuation coecient, d denotes the distance from an object. This

model further decomposes in a form that openly expressed as

(2)

In order to deal with these eects another property volume scattering Β(θ) as:

(3)

The angle θ be integrated to get total scattering f. It theoretically considers all contributions

coming from all directions. Modelling the backward scatter is more complicated than the

forward one because it requires explicit volume scattering function. Four quantities a, b,

c, Β(θ) represents an ocular property of underneath medium. This resulting form used to

predict ocular behaviour of light underneath.

For scattering, absorption as well as other optical properties always strictly related to

specic medium composition. This fact justies variability that we meet in dealing with

them. Therefore, to concern picture arrangement process itself, direct, back-scattered as

well as forward-scattered beam forms three additive total irradiance mechanisms, which

mathematically expressed as:

(4)

Where light received by camera consists of three components: (i) object reect beam with

scattering, (ii) object reect beam without scattering, (iii) back scatter part. For further details

in Jae (1990) crucial quantities E

, E

and E

as well analytical formulas that discussed in

deep with denition of an expression for each part of whole irradiance.

651

https://doi.org/10.17993/3ctecno.2021.specialissue8.645-665

3C Tecnología. Glosas de innovación aplicadas a la pyme. ISSN: 2254 – 4143 Edición Especial Special Issue

Noviembre 2021

Figure 1. Block diagram of Proposed Method.

Source: own elaboration.

3. PROPOSED METHOD

The optical behaviour of beam in water will degrade the obtained pictures taken from

underwater. In order to solve these issues, we intend a Hybrid technique that is able to deblur

and enhance the underwater images depicted in Figure 1. Our hybrid approach consists of

two main steps. In the rst step, the Non-locally centralized method used for deblurring the

scene. It mainly improves sparse restoration and suppresses the sparse coding noise. The

main feature is to train online sub-dictionaries and choosing online sub-dictionary to each

patch, using IST method for solving l1-minimization trouble created using such models.

But it generates some ringing artefacts around the restored boundaries. In the second

step, we introduce a Gradient guided lter (GGF) to improve edge sharpness. Finally, the

output is well enhanced through Non-Locally Centralized Method via Gradient Guided

Filter (NLCM-GGF). Experimental results proved that the projected scheme gives much

enhancement in both quality metrics and visual excellence than conventional technique.

3.1. DEBLURRING ALGORITHM

The deblurring algorithm as depicted in Figure 2, blurred & noisy description (b) attained

with blurring an ideal picture (r) with point spread function (H), then imposing noise (n),

corresponding mathematical formula expressed as follows:

(5)

652

https://doi.org/10.17993/3ctecno.2021.specialissue8.645-665

3C Tecnología. Glosas de innovación aplicadas a la pyme. ISSN: 2254 – 4143 Edición Especial Special Issue

Noviembre 2021

In fact, some unknown quantities higher than known quantities; this problem becomes an

ill-posed problem, which needs some other priori information.

To recover the reconstruction, rst b is sparsely coded to solve minimization problem as:

(6)

Conversely, reconstructing α

from b is the very dicult task. For faithful reconstruction,

we used in Dong et al. (2013) to reduce sparse coded image. The sparse coding noise stage

represents

(7)

By reducing n

we can get better output. To suppress n

, improve α

, we propose the

following model:

(8)

where β

signify ne evaluation of α

γ signify regularize constraint and p will be 1 or 2.

To select dictionary, we cluster the patches by K-means clustering, then uses PCA in each

cluster to nd the sub dictionary. To code each patch, we enforce that particular patch by

keeping sub-dictionaries as zero.

Hence sparse coding model as:

(9)

Where β

represents mass, average related by NL like patches

(10)

where m

i,t

denotes weight. Related to NL means, we set weights as:

(11)

653

https://doi.org/10.17993/3ctecno.2021.specialissue8.645-665

3C Tecnología. Glosas de innovación aplicadas a la pyme. ISSN: 2254 – 4143 Edición Especial Special Issue

Noviembre 2021

where and denotes estimation of patch r

and r

i,t

h represents predestined scalar and

w denotes normalization part.

For each iteration, sparse vector represents:

(12)

For IST process, learning patches updated by present description of reconstruction and

update PCA bases as well as by repeating neighbourhood choice with reorganized learning

information. For every iteration by updating learning set with PCA bases, current test patch

updated by

. The restored representation is then updated as

3.2. GRADIENT GUIDED FILTER (GGF)

The deblurred output better reconstruct the image but it generates a few ring artefacts

around the restored boundaries. With this aim, a Gradient guided lter (GGF) in Kou et

al. (2015) is to improve edge sharpness. The ltered as well as guidance pictures are same

for detailed output. The projected method gives an edge-preserved smooth picture. The

dierence among input with output gives detail layer, which is mainly for strengthening the

output. In an edge, a

denotes

(13)

The rate of a

is nearer to 1 if pixel a

is in boundary, such that sharp boundaries are good

in projected method than conventional technique.

In at area, a

is usually 0 and Γ ̂(d' ) is smaller than 1 denoted as:

(14)

654

https://doi.org/10.17993/3ctecno.2021.specialissue8.645-665

3C Tecnología. Glosas de innovación aplicadas a la pyme. ISSN: 2254 – 4143 Edición Especial Special Issue

Noviembre 2021

Figure 2. Flowchart of Deblurring algorithm.

Source: own elaboration.

In an edge, larger λ chooses for projected method than existing because choice will not aect

edges. This means that projected method smooth at area better than existing technique.

For these two cases the weighing function Γ ̂(d' ) denoted as:

(15)

Where

signify lter window dimension. The projected method is sharper by way of

increasing of

λ. Though, it has fewer artefacts even by larger λ. So, we used larger λ in

projected method exclusive of halo artefacts.

655

https://doi.org/10.17993/3ctecno.2021.specialissue8.645-665

3C Tecnología. Glosas de innovación aplicadas a la pyme. ISSN: 2254 – 4143 Edición Especial Special Issue

Noviembre 2021

3.3. ENHANCEMENT METHOD

After the process of NLCM and GGF, we joined both to improved eminence of

representation. For better reconstruction we employed NLCM method which generate

sharper boundaries and restore best descriptions, but it produces some ringing artefacts

around the reconstructed edges. To avoid these eects, deblurred output takes advantage

of GGF for edge-preservation. The projected NLCM-GGF oer enhanced outcome than

existing techniques for both evaluation metrics and visual perception.

4. RESULTS

Our projected scheme compared by various conventional reconstruction methods:

ASDSARNL in Dong et al. (2011), NCSR in Dong et al. (2013) and DCFGGF in Jiji and

Ramrao (2019). Our method also combines with BF, GF, WGF and GGF. Consequently, it

is obligatory for comparing dierent edge lters to better keep edges. Here we carried out

performance of various techniques, image evaluations.

4.1. Subjective Performance Comparison

Various methods of reconstruction include: ASDSARNL in Dong et al. (2011), NCSM in

Dong et al. (2013), DCFGGF in Jiji and Ramrao (2019), NLCM-BF, NLCM-GF, NLCM-

WF and NLCM-GGF.

To make sure the fairness of each assessment system, all test underwater images are

pre-processed at size 256×256 pixels and processed by evaluated schemes with default

parameters. The results in Dong et al. (2011) generate better visual excellence and evaluation

metrics, though lesser patch dimension produces few artefacts in smooth areas. The results

in Dong et al. (2013) much outperform Dong et al. (2011), produce sharper boundaries and

further restore its quality. The projected smoothing layer in Figure 3 yields improved results

than conventional schemes. Similarly, detail enhancement in Figure 4 is also much clearer

and better than conventional schemes but there exhibit fewer edges in WGF than others. In

Figure 5 we present hybrid result of existing and projected means.

656

https://doi.org/10.17993/3ctecno.2021.specialissue8.645-665

3C Tecnología. Glosas de innovación aplicadas a la pyme. ISSN: 2254 – 4143 Edición Especial Special Issue

Noviembre 2021

Figure 3. Edge smoothing results of Existing and Proposed Method.

Source: own elaboration.

Figure 4. Detail Enhancement results of Existing and Proposed Method.

Source: own elaboration.

657

https://doi.org/10.17993/3ctecno.2021.specialissue8.645-665

3C Tecnología. Glosas de innovación aplicadas a la pyme. ISSN: 2254 – 4143 Edición Especial Special Issue

Noviembre 2021

Figure 5. Enhancing performance evaluation of Underwater Imagery.

Source: own elaboration.

We observed that proposed process results much improved and enhanced details than

conventional process.

4.2. OBJECTIVE PERFORMANCE COMPARISON

Image quality usually aected through imaging equipment, instrument noise, imaging

conditions, image processing and other factors. Image Quality Assessment (IQA) is often

658

https://doi.org/10.17993/3ctecno.2021.specialissue8.645-665

3C Tecnología. Glosas de innovación aplicadas a la pyme. ISSN: 2254 – 4143 Edición Especial Special Issue

Noviembre 2021

separated into subjective qualitative assessment. Gray mean rate of picture reects integral

intensity and expressed as:

(16)

Standard deviation reects high frequency part that relates picture contrast. Higher values

give better contrast.

(17)

Mean gradient reects speed of changes in minor details of picture; it can represent

description of grain transform and quantity of clearness well.

(18)

Entropy interprets as average uncertainty of data. When applied to images, it represents

abundance data observed in picture. Higher entropy gives more uniform contrast

(19)

Mean Square averages squared intensity dierences of among distorted and reference

representation as

(20)

where R, C denotes row and column, O(r,c) remains original with O’(r,c) denotes deblurred

picture. Peak SNR (PSNR) signify a key meant for signal alteration.

(21)

Where O

max

represents maximum gray rate. Higher PSNR value represents lesser distortion.

Generally, ocular view in Wang and Yuan (2017) and Wang et al. (2004) particularly

adapted to extract picture information, thus process image excellence by three mechanism

specically; luminance l(I,O), contrast C(I,O), structure comparison S(I,O). Thus, similarity

computation represents

659

https://doi.org/10.17993/3ctecno.2021.specialissue8.645-665

3C Tecnología. Glosas de innovación aplicadas a la pyme. ISSN: 2254 – 4143 Edición Especial Special Issue

Noviembre 2021

(22)

The similarity of two images has a rate among [0, 1]. When it is close to 1, two descriptions

are more similar.

In Yang and Sowmya (2015) underwater color image quality evaluation (UCIQE) represents

contrast, chroma and saturation expressed as:

(23)

Where σ

, con

and μ

represent standard deviation, contrast and mean, c

, c

represent

these three weights. Higher UCIQE metrics have improved results than conventional

schemes. Similar to UCIQE, undersea image quality measure (UIQM) in Panetta, Gao,

and Agaian (2016) constructed linear combination of UI colorfulness metric (UICM), UI

sharpness metric (UISM) and UI contrast metric (UIConM). Thus, larger UCIQE and

UIQM, improved undersea color image quality will be.

(24)

Where α, β,

γ signies weight coecients to organize each measure as well as balance

their rates. Higher UICM value indicates improved color of undersea descriptions. Table 1

shows assessment metrics of conventional and projected technique.

Table 1. Comparison of quality metric with existing and proposed methods.

Methods

DEBLURRED IMAGE ENHANCED IMAGE

(Dong et

al., 2011)

(Dong et

al., 2013)

(Jiji &

Ramrao,

2019)

NLCM-BF NLCM-GF NLCM-WGF NLCM-GGF

Mean 127.34 127.36 96.639 126.81 126.73 127.22 127.29

SD 71.236 71.153 67.783 94.869 86.831 77.084 74.339

AG 9.226 8.065 10.194 23.761 18.507 12.988 11.681

Entropy 7.933 7.941 7.541 6.351 6.984 7.536 7.619

PSNR 24.10 26.231 65.843 66.916 70.956 72.255 72.417

RMSE 13.717 0.752 0.139 0.115 0.072 0.062 0.061

SSIM 0.619 12.443 0.9977 0.9990 0.9997 0.9998 0.9998

UICM -45.558 -45.555 -62.107 -33.899 -39.299 -43.522 -44.177

Quality

metrics

660

https://doi.org/10.17993/3ctecno.2021.specialissue8.645-665

3C Tecnología. Glosas de innovación aplicadas a la pyme. ISSN: 2254 – 4143 Edición Especial Special Issue

Noviembre 2021

UIConM 0.736 0.728 0.785 0.305 0.583 0.701 0.681

UISM 6.906 7.007 7.105 7.827 7.289 7.057 7.073

UIQM 3.389 3.388 3.155 2.449 3.131 3.364 3.278

UCIQE 32.073 32.112 35.233 35.597 33.729 32.548 32.423

Source: own elaboration.

5. CONCLUSIONS

An acquired image underneath water gets degraded due to optical properties of light

in water. However, due to degradation of observed picture, conventional forms are not

correct enough for faithful reconstruction. In this paper, we proposed a hybrid technique

for improving undersea descriptions. First, we used a Non locally centralized (NLCM)

method for deblurring underwater descriptions, later gradient guided lter algorithm to

improve the visibility of picture details and nally a Hybrid technique called non-locally

centralized gradient guided lter (NLCM-GGF) gives improved results. Experimental

results of proposed technique perform better than many conventional techniques together

in quality metrics and visual evaluation. Nevertheless, when the illumination is very uneven,

enhancement limits the local dark region, and it requires further research.

ACKNOWLEDGEMENT

We gratefully thank the Visvesvaraya Technological University, Jnana Sangama, Belagavi

for their extended support to this Research work.

REFERENCES

Banham, M. R., & Katsag, A. K. (1997). Digital image restoration. IEEE Signal Processing

Magazine, 14(2), 24-41. https://doi.org/10.1109/79.581363

Beck, A., & Teboulle, M. (2009). Fast Gradient-Based Algorithms for Constrained Total

Variation Image Denoising and Deblurring Problems. IEEE Transactions on Image

Processing, 18(11), 2419-2434. https://doi.org/10.1109/TIP.2009.2028250

Bertero, M., & Boccacci, P. (1998). Introduction to Inverse Problems Imaging. CRC Press.

661

https://doi.org/10.17993/3ctecno.2021.specialissue8.645-665

3C Tecnología. Glosas de innovación aplicadas a la pyme. ISSN: 2254 – 4143 Edición Especial Special Issue

Noviembre 2021

Bioucas-Dias, J. M., & Figueiredo, M. A. T. (2007). A New TwIST: Two-Step Iterative

Shrinkage/Thresholding Algorithms for Image Restoration. IEEE Transactions on

Image Processing, 16(12), 2992-3004. https://doi.org/10.1109/TIP.2007.909319

Buades, A., Coll, B., & Morel, J.-M. (2005). A review of image denoising algorithms,

with a new one. Multiscale Modeling and Simulation: A SIAM Interdisciplinary Journal,

Society for Industrial and Applied Mathematics, 4(2), 490-530. hal-00271141f. https://

hal.archives-ouvertes.fr/hal-00271141/document

Chan, T., Esedoglu, S., Park, F., & Yip A. (2005). Recent developments in total variation image

restoration. http://vision.mas.ecp.fr/paragios-chen-faugeras/sample.pdf

Chantas, G., Galatsanos, N. P., Molina, R., & Katsaggelos, A. K. (2010). Variational

Bayesian Image Restoration With a Product of Spatially Weighted Total Variation

Image Priors. IEEE Transactions on Image Processing, 19(2), 351-362. https://doi.

org/10.1109/TIP.2009.2033398

Daubechies, I., Defrise, M., & De Mol, C. (2004). An iterative thresholding algorithm

for linear inverse problems with a sparsity constraint. Communications on Pure and

Applied Mathematics, 57(11), 1413-1457. https://doi.org/10.1002/cpa.20042

Dong, W., Zhang, L., & Shi, S. (2011). Centralized sparse representation for image

restoration. In International Conference on Computer Vision, 1259-1266. https://doi.

org/10.1109/ICCV.2011.6126377

Dong, W., Zhang, L., Shi, G., & Li, X. (2013). Nonlocally Centralized Sparse

Representation for Image Restoration. IEEE Transactions on Image Processing, 22(4),

1620-1630. https://doi.org/10.1109/TIP.2012.2235847

Dong, W., Zhang, L., Shi, G., & Wu, X. (2011). Image Deblurring and Super-Resolution

by Adaptive Sparse Domain Selection and Adaptive Regularization. IEEE Transactions

on Image Processing, 20(7), 1838-1857. https://doi.org/10.1109/TIP.2011.2108306

Farbman, Z., Fattal, R., Lischinski, D., & Szeliski, R. (2008). Edge-preserving

decompositions for multi-scale tone and detail manipulation. ACM Transactions on

Graphics, 27(3), 1-10. https://doi.org/10.1145/1360612.1360666

662

https://doi.org/10.17993/3ctecno.2021.specialissue8.645-665

3C Tecnología. Glosas de innovación aplicadas a la pyme. ISSN: 2254 – 4143 Edición Especial Special Issue

Noviembre 2021

He, K., Sun, J., & Tang, X. (2013). Guided image ltering. http://kaiminghe.com/

publications/eccv10guidedlter.pdf

Huimin, L., Yujie, L., Lifeng, Z., & Seiichi, S. (2015). Contrast enhancement for

images in turbid water. Journal of the Optical Society of America A, 32(5), 886-893.

https://www.osapublishing.org/viewmedia.cfm?r=1&rwjcode=josaa&uri=josaa-

32-5-886&html=true

Jae, J. S. (1990). Computer modeling and the design of optimal underwater imaging

systems. IEEE Journal of Oceanic Engineering, 15(2), 101-111. https://doi.

org/10.1109/48.50695

Jiji, A. C., & Ramrao, N. (2017). Deblurring Underwater image degradations based on adaptive

regularization. ICICI.

Jiji, A. C., & Ramrao, N. (2019). A Novel Imaging System for Underwater Haze

Enhancement. International Journal of Information Technology, 12, 85-90. https://link.

springer.com/article/10.1007/s41870-019-00312-y

Jiji, A. C., & Vivek, M. (2017). Underwater turbidity removal through ill-posed

optimization with sparse modelling. In 2017 IEEE International Conference on Power,

Control, Signals and Instrumentation Engineering (ICPCSI), pp. 1865-1869. https://doi.

org/10.1109/ICPCSI.2017.8392039

Kindermann, S., Osher, S., & Jones, P. W. (2005). Deblurring and denoising of images

by nonlocal functional. Multiscale Modeling & Simulation, 4(4), 1091-1115. https://doi.

org/10.1137/050622249

Kou, F., Chen, W., Wen, C., & Li, Z. (2015). Gradient Domain Guided Image Filtering.

IEEE Transactions on Image Processing, 24(11), 4528-4539. https://doi.org/10.1109/

TIP.2015.2468183

Lebart, K., Smith, C., Trucco, E., & Lane, D. (2003). Automatic indexing of

underwater survey video: algorithm and benchmarking method. IEEE Journal of

Oceanic Engineering, 28(4), 673-686. https://doi.org/10.1109/JOE.2003.819314

663

https://doi.org/10.17993/3ctecno.2021.specialissue8.645-665

3C Tecnología. Glosas de innovación aplicadas a la pyme. ISSN: 2254 – 4143 Edición Especial Special Issue

Noviembre 2021

Li, Z., Zheng, J., Zhu, Z., Yao, W., & Wu, S. (2015). Weighted Guided Image Filtering.

IEEE Transactions on Image Processing, 24(1), 120-129. https://doi.org/10.1109/

TIP.2014.2371234

Lysaker, M., & Tai, X. C. (2006). Iterative Image Restoration Combining Total Variation

Minimization and a Second-Order Functional. International Journal of Computer Vision,

66, 5–18. https://doi.org/10.1007/s11263-005-3219-7

Mairal, J., Bach, F., Ponce, J., Sapiro, G., & Zisserman, A. (2009). Non-local sparse

models for image restoration. In 2009 IEEE 12th International Conference on Computer

Vision, pp. 2272-2279. https://doi.org/10.1109/ICCV.2009.5459452

Mairal, J., Elad, M., & Sapiro, G. (2008). Sparse Representation for Color Image

Restoration. IEEE Transactions on Image Processing, 17(1), 53-69. https://doi.

org/10.1109/TIP.2007.911828

Oliveira, P. J., Bioucas-Dias, J. M., & Figueiredo, M. A. T. (2009). Adaptive total

variation image deblurring: A majorization-minimization approach. Signal Processing,

89(9), 1683-1693. https://doi.org/10.1016/j.sigpro.2009.03.018

Panetta, K., Gao, C., & Agaian, S. (2016). Human-Visual-System-Inspired Underwater

Image Quality Measures. IEEE Journal of Oceanic Engineering, 41(3), 541-551. https://

doi.org/10.1109/JOE.2015.2469915

Seibert, Q. (1963). Light in the sea. Journal of the Optical Society of America, 53(2), 214-233.

https://doi.org/10.1364/JOSA.53.000214

Strachan, N. (1993). Recognition of sh species by color and shape. Image and Vision

Computing, 11(1), 2-10. https://doi.org/10.1016/0262-8856(93)90027-E

Tomasi, C., & Manduchi, R. (1998). Bilateral ltering for gray and color images.

Proceedings of the 1998 IEEE International Conference on Computer Vision. https://users.soe.

ucsc.edu/~manduchi/Papers/ICCV98.pdf

Torres-Méndez, L. A., & Dudek, G. (2005) Color Correction of Underwater Images

for Aquatic Robot Inspection. In: Rangarajan, A., Vemuri, B., & Yuille, A.L. (eds.),

664

https://doi.org/10.17993/3ctecno.2021.specialissue8.645-665

3C Tecnología. Glosas de innovación aplicadas a la pyme. ISSN: 2254 – 4143 Edición Especial Special Issue

Noviembre 2021

Energy Minimization Methods in Computer Vision and Pattern Recognition. EMMCVPR

2005. Lecture Notes in Computer Science, vol. 3757. Springer, Berlin, Heidelberg.

https://doi.org/10.1007/11585978_5

Wang, W., & Yuan, X. (2017). Recent advances in image dehazing. IEEE/CAA Journal of

Automatica Sinica, 4(3), 410-436. https://doi.org/10.1109/JAS.2017.7510532

Wang, Z., Bovik, A. C., Sheikh, H. R., & Simoncelli, E. P. (2004). Image quality

assessment: from error visibility to structural similarity. IEEE Transactions on Image

Processing, 13(4), 600-612. https://doi.org/10.1109/TIP.2003.819861

Wu, X., Zhang, X., & Wang, J. (2009). Model-Guided Adaptive Recovery of Compressive

Sensing. In 2009 Data Compression Conference, pp. 123-132. https://doi.org/10.1109/

DCC.2009.69

Yang, M., & Sowmya, A. (2015). An Underwater Color Image Quality Evaluation Metric.

IEEE Transactions on Image Processing, 24(12), 6062-6071. https://doi.org/10.1109/

TIP.2015.2491020

Zhang, X., Burger, M., Bresson, X., & Osher, S. (2010). Bregmanized nonlocal

regularization for deconvolution and sparse reconstruction. SIAM Journal on Imaging

Sciences, 3(3), 253-276. https://epubs.siam.org/doi/10.1137/090746379

665

https://doi.org/10.17993/3ctecno.2021.specialissue8.645-665

3C Tecnología. Glosas de innovación aplicadas a la pyme. ISSN: 2254 – 4143 Edición Especial Special Issue

Noviembre 2021