International Journal of Scientific Research Engineering & Technology (IJSRET), ISSN 2278 0882

Volume 4 Issue 4, April 2015

Underwater Image Enhancement for Improving the Visual

Quality by CLAHE Technique
DITHEE DEV K1, Mr. S.NATRAJAN2
1
P.G Scholar, 2Assistant Professor
Dept. of Communication Systems, Nehru Institute of Engineering and Technology, CBE

ABSTACT
The processing of underwater image capture is necessary
because the quality of underwater images may lead some
serious problems when compared to images from a
clearer environment. A lot of noise occurs due to low
contrast, poor visibility conditions (absorption of natural
light), non uniform lighting and little color variations,
pepper noise and blur effect in the underwater images
because of all these reasons number of methods are
existing to cure these underwater images. The one of the
effective method is used to improve the underwater
image is the contrast limited adaptive histogram
equalization (CLAHE) technique. From the underwater
input image calculate th.e dark channel and is processed
under the image segmentation. Then find out whether it
contains the influence of artificial light or not. If it is yes
remove it using appropriate method and then go for the
CLAHE technique. The experimental results of this
method significantly improve the visual quality of
underwater images by enhancing contrast as well as the
noise and artifacts.
Keywords- CLAHE Technique, dark channel, depth map,
image enhancement, underwater photography

I.

INTRODUCTION

Underwater photography is the process of

taking photographs in underwater. It is usually done
while scuba diving but can be done while diving on
surface supply, snorkeling, swimming from a
submersible or remotely operated underwater vehicle or
from automated cameras lowered from the surface.
Underwater photography can also be categorized as an
art form and method of recording data. Successful
underwater imaging is always done with specialized
equipment and techniques. However it offers exciting
and rare photographic opportunities. Animals such as
fish and marine mammals are common subjects, but
photographers also pursue shipwrecks, submerged cave
systems, underwater landscapes, invertebrates, seaweeds,
geological features, and portraits of fellow divers. The
underwater image processing area has received
considerable attention within the last decades, showing
important achievements such as digging of ocean bottom
resources, exploration of aquatic environment, rescues
and salvages have increased. There are some of the most

recent methods that have been specifically developed

for the underwater environments. These techniques
are capable of extending the range of underwater
imaging, improving image contrast and resolution.
The conditions for which each of them has been
originally developed are highlighted as well as the
quality assessment methods used to evaluate their
performance.
The primary obstacle faced by underwater
photographers is the loss of color and contrast when
submerged to any significant depth. The longer
wavelengths of sunlight (such as red or orange) are
absorbed quickly by the surrounding water, so even
to the naked eye everything appears blue-green in
color. The loss of color not only increases vertically
through the water column, but also horizontally, so
subjects further away from the camera will also
appear colorless and indistinct. This effect is true
even in apparently clear water, such as that found
around tropical coral reefs. Another environmental
effect is range of visibility. The water is seldom
optimally clear, and the dissolved and suspended
matter can reduce visibility by both absorption and
scattering of light. The visibility range can be
increased with artificial lighting but these sources not
only suffer from the difficulties described before
(scattering and absorption), but in addition tend to
illuminate the scene in a non uniform fashion,
producing a bright spot in the center of the image
with a poorly illuminated area surrounding it.

Fig.1.1Graph of light absorption coefficient of pure

water
It is difficult to observe underwater
environments with cameras because of viewdisturbing noises, light refraction effects and
attenuation effects. The first problem is about

www.ijsret.org

352

International Journal of Scientific Research Engineering & Technology (IJSRET), ISSN 2278 0882
Volume 4 Issue 4, April 2015

suspended particles such as bubble noises small fishes,

and small creatures in the underwater environment. They
may disturb cameras field of view. The second problem
is about the light refraction effects because of the two
different medium. The third problem is about the
attenuation effects of light, when the light intensity
decreases the distance from objects in water by this
phenomenon depending on the wavelength of light.
There are lots of techniques used nowadays to
compensate the difficulties of underwater photography.
Our proposed method is used to improve the visibility by
eliminating the scattering effect, color change and
different kind of noises which affect the underwater
environment.

EXISTING METHODS
The processing of underwater image captured [4]
is necessary because the quality of underwater images
becomes worse and this image leads some serious
problems when compared to images from a clearer
environment. A lot of noise occurs due to low contrast,
poor visibility conditions (absorption of natural light),
non uniform lighting and little color variations, pepper
noise and blur effect in the underwater images. Because
of all these reasons number of methods are existing to
cure these underwater images i.e., different filtering
techniques are also available in the literature for
processing and enhancement of underwater images one
of them is image enhancement using median filter which
enhances the image and help to estimate the depth map
and improve quality by removing noise particles with the
help of different techniques, and the other is RGB Color
Level Stretching have used. Forward USM technique can
also be used as one of the image enhancement process.
Mostly underwater image enhancement focuses
solely on compensating either light scattering or color
change distortion. The technique targeting on removal of
light scattering distortion include exploiting the
polarization effects to compensate for visibility
degradation[9], using image dehazing to restore the
clarity of underwater images[7], and combining point
spread functions and a modulation transfer function to
reduce the blurring effect[8].Although the earlier
approaches can enhance scene contrast and increase the
visibility, distortion caused by disparity in wavelength
attenuation, that is color change remains same.

removing the blurriness caused by light scattering. A

systematic approach is needed to take all the factors
that are light scattering color change and possible
presence of artificial light in to consideration.
Recently the researchers found WCID (wavelength
compensation and image dehazing) algorithm shows
a good result over these image enhancement
problems. Though it is an effective algorithm in all
those scattering and color change problems, it shows
lack of visibility in underwater images due to some
noises and artifacts. To eliminate these kind of
unwanted items from underwater images and also
compensate the light scattering and color change we
are going for another kind of technique in our
proposed method. To avoid these kind of noises we
are doing some filtering operations.

II.

PROPOSED METHOD

2.1 Underwater Image Enhancement by CLAHE

Technique
Adaptive histogram equalization and contrast
limited adaptive histogram equalization were
proposed to overcome the over amplification of noise
problem. While performing AHE if the region being
processed has a relatively small intensity range then
the noise in the region gets more enhanced. It can
also cause some kind of artifacts to appear on those
regions. To limit the appearance of such artifacts and
noise, a modification of AHE called contrast limited
AHE can be used. Contrast limited adaptive
histogram equalization (CLAHE) is an adaptive
contrast histogram equalization method ,where the
contrast of an image is enhanced by applying
CLAHE on small data regions called tiles rather than
the entire image. The resulting neighboring tiles are
then stitched back seamlessly using bilinear
interpolation.
The contrast in the homogeneous region can be
limited so that noise amplification can be avoided.

On the other hand color change correction

techniques
estimate
underwater
environmental
parameters by performing color registration with
consideration of light attenuation, employing histogram
equalization in both RGB and HSV color spaces to
balance the luminance distribution of color. Despite the
improved color balance, these methods are not fully
www.ijsret.org

Fig.2.1. Flow chart of proposed system

353

International Journal of Scientific Research Engineering & Technology (IJSRET), ISSN 2278 0882
Volume 4 Issue 4, April 2015

The algorithm for Contrast Limited Adaptive

Histogram Equalization (CLAHE) technique is to
remove distortion caused by light scattering and color
change. Dark-channel prior an existing scene-depth
derivation method is used to estimate the distance of the
scented object to the camera. The low intensities of the
dark channel are mainly due to shadows, colorful objects
or surfaces and dark object or surfaces. Based on the
depth map derived, the foreground and background areas
within the image are segmented. The light intensities of
foreground and background are then compared to
determine whether an artificial light source is employed
during the image acquiring process. If an artificial light
source is detected, the luminance introduced by the
auxiliary lighting is removed from the foreground area to
avoid the overcompensation in the stages followed. Next
the dehazing algorithm and CLAHE are utilized to
remove the haze effect and color change along the
underwater propagation path to the camera. The residual
ratio among different color channels in the background
light is employed to estimate the water depth within an
underwater scene. Energy compensation for each color
channel is carried out subsequently to adjust the bluish
tone to a natural color. With CLAHE, expensive optical
instrument or stereo image pairs are no longer required.
CLAHE can effectively enhance visibility and restore the
color balance of underwater images, rendering high
visual clarity and color fidelity and also avoid the noise
and artifacts.

III.

EXPERIMENTAL RESULT

In contrast limited adaptive histogram

equalization technique, first the distance between the
scenes objects to camera is estimated by using a low
complexity dark channel prior algorithm. Based on the
depth map derived the foreground and background area
within the image is segmented. The light intensities of
foreground and background are then compared, to
determine whether an artificial light source is employed
during the image acquiring process. If an artificial light
source is detected, the added luminance is to be
eliminated. The CLAHE technique is utilized to remove
the haze effect and color change along the underwater
propagation path. The results of each stage are given in
the following steps.

flash light of camera for avoiding the insufficient

lighting in photographic environment or without the
artificial light if the environment is clear. The light
from both the camera and artificial light source is
incident on surface points in the scene and reflected
back to camera. In the propagation path between the
subject and camera d(x), hazing and color distortion
occurs due to the light scattering and varying degrees
of attenuation encountered with different wavelength
of light. The homogeneous skylight entering above
into the water is the major source of illumination in
an underwater environment.

Fig.3.1.The underwater photographic system

3.2 Dark Channel Prior Algorithm
We propose a simple but effective dark
channel prior to remove haze from a single input
image. The dark channel prior is a type of statistics
of outdoor haze free images. It is based on a key
observation that most local patches in outdoor haze
free image contain some pixels whose intensity is
very low in at least one color channel. Using this
prior with the haze image model, we can directly
estimate the thickness of the haze and recover the
high quality haze free image. Result of the different
variety of haze images demonstrates the power of the
proposed prior. Moreover a high quality depth map
can also be obtained as a byproduct of the haze
removal. The depth map will estimate the distance
between object to camera from that we can
understand the intensity level of the light in the
underwater environment. The following equations
are used to produce dark channel prior result.
The underwater image haze can be modeled by
Radiative transport equation

3.1 Underwater Photographic System

I(x)= j(x).t(x) + (1-t(x)).B

Homogeneous light above in to the water is the

major source of illumination in the underwater
environment. Incident light travels from the surface of
the water reaching the image scene, covering a range of
depth through the addition of depth and image depth
range. The underwater photographic system is either
provided with an artificial light source in addition to

Where { red, green, blue}

Dark channel= max (min (I(x)))

... (1)

... (2)

Depth map= 1-min {median (I(x)/B)} ... (3)

where the median is used to reduce the block effect.

www.ijsret.org

354

International Journal of Scientific Research Engineering & Technology (IJSRET), ISSN 2278 0882
Volume 4 Issue 4, April 2015

The foreground and background areas of the

underwater images are segmented based on the depth
map derived using a threshold. If the distance between
the object and camera is greater than the threshold it is
considered as the foreground otherwise it is the
background.

3.4 Removal of Artificial Light

The luminance contributed by the artificial
light source has to be removed before the Contrast
Limited Adaptive Histogram Equalization Technique
to avoid the overcompensation caused by the presence
of artificial light. These are the steps:

3.3 Determination of Artificial Light

1. Calculate the average intensity of both the
foreground and background images.

Artificial light is provided to overcome

insufficient lighting commonly encountered in an
underwater photography environment. The existence of
the artificial light source can be determined by
comparing the difference between the mean luminance
of the foreground and background images. Higher
mean luminance in the foreground indicates the
existence of a supplementary light source.

(a)

(b)

2. Take the difference between foreground intensity

and background intensity.
3. Find the luminosity updated foreground intensity.
4. The image free of artificial light source is obtained
by adding the foreground with the background.

(c)

(d)

(e)

Fig.3.2. (a)input image (b)dark channel (c)image segmentation (d)luminance of input image (e)dehazed image using
CLAHE.

(f)
(g)
(h)
(i)
(j)
Fig.3.3.Images with the influence
of artificial
light (f)input Image (g)dark channel (h)image
Segmentation (i)luminance of input image (j)dehazed image using CLAHE

www.ijsret.org

355

International Journal of Scientific Research Engineering & Technology (IJSRET), ISSN 2278 0882
Volume 4 Issue 4, April 2015

3.5 Compensation of Light Scattering and Color

Change

REFERENCES
[1].Wan Nural Hi Yusof, Muhammed Suzuri,
Performing Contrast Limited Adaptive
Histogram
Equalization
Technique
on
combined color models for underwater image
enhancement
International Journal
on
Interactive
Digital
Media,
Vol.1(1),
ISSN:2289-4101, Feb 2014.

After removing the artificial light source and deriving

distance d(x) between an object and camera, the haze can
be removed by subtracting the in-scattering term from it.
Then we are going for contrast limited adaptive
histogram equalization technique. In contrast limited
adaptive histogram equalization, it will equalize all the
colors by clipping method hence our scattering effect and
color change will be compensated. The noises will be
removed by using spatial filters. Then we got a high
quality image with increased visibility.

IV.

[2].John y .Chiang and Ying Chen Underwater

Image
Enhancement
by
Wavelength
Compensation
and
Dehazing
IEEE
Transaction of image processing, Vol.21, No.4.
April 2012.

CONCLUSION

The underwater image suffers from low contrast

and resolution due to poor visibility conditions, hence an
object identification become typical task.
This paper proposes a contrast limited adaptive
histogram equalization algorithm for enhancing the
underwater images and performs the illuminant
estimation due to the presence of artificial light. The
CLAHE algorithm that effectively performs the better
clarity of the image the hazy effect cause in presence of
scattering and color changing. It gives better result
compared to another methods like WCID, polarization
analysis etc. and also the enhancement methods
effectively improves the visibility of underwater images
and produce the lowest MSE values and the highest
PSNR values. This enhancement method appears to be
useful for a wide range of underwater images
application.

[3].Kashif
Iqbal
,Rosalina
Abdul
Salam,
Underwater Image Enhancement Using an
Integrated Color model IAENG International
journal
of
computer
science,IJCS_34_2_12,Nov2007.
[4].Della Raju and Jaini Sara Babu,Removal of
artificial light source and image dehazing in
underwater image using WCID algorithm
International journal for Engineering Research and
Technology, ISSN: 2278-0181,March2014.
[5].Alka Tripathi, Ms.Pragya Gupta, Dr.Vineeth
Richaria,Haze Removal and Color Compensation
of Underwater Image and Dehazing, IJCSIT,
vol.5 (3), ISSN: 0975-9646,March2014.
[6].Karthiga R and Ashok Raj.M,Illuminance
estimation in underwater using color constancy,
CARE Journal of Applied Research, IISN: 23214090.
[7].Y.Y.Schechner and N.Karpel,Recovery of
Underwater Visibility and Structure by
Polarization Analysis,IEEE J.Ocean.Eng., vol30,
no.3, July2005.
[8].L.Chao and M.Wang,Removel of water
scattering, in Proc. Int. Conf. Computer.
Eng.Technol.2010, vol 2, pp.35-39.

Fig.3.4 Comparison of WCID method with CLAHE

technique

[9].Pooja Sahu, Neelesh Gupta and Neethu

Sharma,A Survey on underwater image
enhancement techniques, international journal of
computer allocation 87(13):19-23, Feb 2014.

www.ijsret.org

356