You are on page 1of 10

Abstract: Lowered pictures expect a basic part in ocean examination, anyway consistently

experience the evil impacts of extraordinary quality corruption due to light ingestion and
scattering in water medium. Though huge accomplishments have been made starting late in
the general locale of picture overhaul and, the propriety of new methods for improving the
idea of lowered pictures has not expressly been gotten. In this paper, we overview the image
overhaul strategies that tackle average lowered picture impediments, including some silly
degradations and mutilations. we pinpoint the basic lacks of existing techniques.

Key words: RGB(Red, Green, Blue), Hue, Saturation, Intensity, Adaptive histogram
equalization, Gamma correction, Integrated Colour Model, Adaptive Parameter Acquisition,
Unsupervised Colour Correction Method, Contrast.

Introduction: The underwater image suffers degradation due to scattering and absorption. To
overcome these issues, the acquired images are adjusted using color balance and then
corrected using white balance. Underwater images are affected by reduced contrast and non-
uniform color cast due to the absorption and scattering of light in the aquatic environment.
This affects the quality and reliability of image processing and therefore color correction is a
necessary pre-processing stage. The oceans contain unknown creatures and vast energy
resources, playing an important role in the continuation of life on earth. Since the middle of
the 20th century, marine exploration worldwide has actively engaged in high-tech activities.
Vision technology has attracted great attention, for its ability to carry high information
density. Researchers strive to capture high-quality underwater images for a variety of
underwater applications, including robotics, rescue missions, man-made structures inspection,
ecological monitoring, sea organisms tracking and real-time navigation. In any case, the idea
of lowered pictures is genuinely impacted by the particular physical and engineered
characteristics of lowered conditions, raising issues that are on the whole the more adequately
rout in terrestrial imaging. Lowered pictures reliably show concealing cast, e.g., green bluish
concealing, which is achieved by different debilitating extents of red, green and blue lights.
Moreover, the particles that are suspended lowered absorb the majority of light energy and
adjust the course of light before the light reflected from lowered scene shows up at the
camera, which prompts pictures having low-distinction, dark and haze. In order to extend the
extent of lowered imaging, counterfeit light sources are every now and again used. In any
case, counterfeit light additionally is impacted by maintenance and scattering. The
specialized hardware platforms and cameras can be expensive and power-consuming. What is
more, they are not adaptive to different underwater environments. Thus, many algorithmic
methods have been developed for underwater image quality improvement by image
enhancement.

Existing System Survey:


1. GC: Gamma Correction Gamma correction, or often simply gamma, is a nonlinear
operation used to encode and decode luminance or tristimulus values in video or still

1
image systems. Gamma encoding of images is used to optimize the usage of bits when
encoding an image, or bandwidth used to transport an image, by taking advantage of
the non-linear manner in which humans perceive light and colour. The human
perception of brightness, under common illumination conditions, follows an
approximate power function, with greater sensitivity to relative differences between
darker tones than between lighter tones, consistent with the Stevens power law for
brightness perception.

2. HE: Histogram Equalization, Histogram equalization is a method in image processing


of contrast adjustment using the image's histogram.

3. ICM: Integrated Colour Model, In underwater situations, clarity of images z degraded


by light absorption and scattering. This causes one colour to dominate the image. In
order to improve the perception of underwater images, we proposed an approach
based on slide stretching. The objective of this approach is twofold. Firstly, the
contrast stretching of RGB algorithm is applied to equalize the colour contrast in
images. Secondly, the saturation and intensity stretching of HSI is used to increase the
true colour and solve the problem of lighting.

4. RGHS: Relative Global Histogram Stretching, Based on Adaptive Parameter


Acquisition: RGHS method based on adaptive parameter acquisition. The proposed
method consists of two parts: contrast correction and colour correction. The contrast
correction in RGB colour space firstly equalizes G and B channels and then
redistributes each R-G-B channel histogram with dynamic parameters that relate to
the intensity distribution of original image and wavelength attenuation of different
colours under the water. The bilateral filtering is used to eliminate the effect of noise
while still preserving valuable details of the shallow-water image and even enhancing
local information of the image.

The colour correction is performed by stretching the 'L' component and modifying 'a' and 'b'
components in CIE-Lab colour space. Experimental results demonstrate that the proposed
method can achieve better perceptual quality, higher image information entropy, and less
noise, compared to the state-of-the-art underwater image enhancement methods.

Requirements: Libraries need to install to execute the code-


 Python 3.6
 Cv2
 NumPy
 SciPy
 Matplotlib

2
 Scikit-image
 Natsort
 Math
 Datetime

Proposed System: Underwater images are affected by reduced contrast and non-uniform
colour cast due to the absorption and scattering of light in the aquatic environment. This
affects the quality and reliability of image processing and therefore colour correction is a
necessary pre-processing stage. In this technique, we propose a hybrid algorithm
Unsupervised Colour Correction Method (UCM) and contrast limited adaptive histogram
equalization (CLAHE) for underwater image enhancement. It is based on colour balancing,
contrast correction of RGB colour model and contrast correction of HSI colour model.

Flowchart:

Balanced RGB Contrast correction for


Input Image
colors RGB model

Contrast correction Low


of red or blue red/high
Y
color(one side) blue

N
HSI model contrast
correction Contrast correction for
green color(both sides)

Output Image Contrast correction of saturation and intensity components( dark


side and light side)

Methodology:

1. Firstly, the color cast is reduced by equalizing the color values


2. Secondly, an enhancement to a contrast correction method is applied to increase the red
color by stretching red histogram towards the maximum
3. Ssimilarly the Blue color is reduced by stretching the blue histogram towards the
minimum

3
4. Thirdly, the Saturation and Intensity components of the HSI color model have been
applied for contrast correction to increase the true color using Saturation and to address the
illumination problem through Intensity.

Unsupervised Color Correction Method (UCM), which can efficiently remove bluish color
cast, increase the low red and low illumination problem in order to achieve high quality
images for scientific purpose.

CLAHE is a variant of Adaptive histogram equalization (AHE)  which takes care of over-
amplification of the contrast. CLAHE operates on small regions in the image, called tiles,
rather than the entire image. The neighbouring tiles are then combined using bilinear
interpolation to remove the artificial boundaries.

Our proposed approach is based on the following three stages:

A. Equalize the RGB colors .

B. Contrast correction of RGB color model .

C. Contrast correction of HSI color model.

Results and Comparison:

For comparison of results, we used the Image Quality Assessment Metric ENTROPY.

Screenshot of the results:- [UCM]+[CLAHE]

4
TECHNIQUES USED FOR IMAGE ENTROPY LEVEL
ENHANCEMENT

GAMA CORRECTION 7.65

HISTOGRAM EQUILIZATION 7.57

INTEGRATED COLOUR MODEL 7.56

UCM+CLAHE 7.71

By the comparison of Entropy results , UCM+CLAHE tops list with the ENTROPY 7.715.

Source code consists of Image enhancement in the attributes associated- Colour and Picture Quality

DATA SET:

INPUT IMAGES: OUTPUT IMAGES:

5
6
LOW LIGHT IMAGES:

7
8
Conclusion: Quality improvement methods of underwater images based on image
enhancement helped us. In this review, we firstly gave introduction to the basic principles of
underwater images. We provided comparison of the quality improvement methods using
ENTROPY. The underwater image enhancement methods have made good progress. Still
there is no algorithm that can be applied to enhance underwater images taken from diverse
environment and depths. The adaptability of underwater image enhancement methods still
needs to be improved. Current underwater image enhancement methods focus on improving
the perceptual effect of images but ignore whether the enhanced images can increase the
accuracy of high-level feature analysis such as target detection and classification. Improving
the quality of underwater images can effectively release the pressure of high-level underwater
tasks. The existing underwater image enhancement methods are not able to recover deep sea
images. So new imaging models for deep sea imaging environment is needed.

References:
[1]
https://arxiv.org/abs/1903.09766

Er. Charanjeet Kaur, Er. Rachna Rajput (May 2015). a review on “underwater image
[2]

quality enhancement using adaptive gamma correction weighting distribution”,


International Journal of Engineering Research and Management (IJERM).

K. Kim, J. Kim, S. Kang, J. Kim, and J. Lee, (2012). “Object recognition for cell
[3]

manufacturing system,” in 2012 9th International Conference on Ubiquitous Robots and


Ambient Intelligence (URAI), pp. 512–514.

H. Lu, T. Uemura, D. Wang, J. Zhu, Z. Huang, and H. Kim, (2018). “Deep-Sea


[4]

Organisms Tracking Using Dehazing and Deep Learning,” Mob. Netw. Appl., Oct.

B. McGlamery, (1979) “A computer model for underwater camera system,” in Ocean


[5]

Optics VI, S. Q. Duntley, Ed., vol. 208 of Proceedings of SPIE, pp. 221–231.

9
J. S. Jaffe, (1990). “Computer modelling and the design of optimal underwater imaging
[6]

systems,” IEEE Journal of Oceanic Engineering, vol. 15, no. 2, pp. 101–111.

C. Funk, S. Bryant, and P. Heckman, (1972). “Handbook of underwater imaging system


[7]

design,” Tech. Rep. TP303, Naval Undersea Centre, San Diego, Calif, USA.
[8]
T. H. Dixon, T. J. Pivirotto, R. F. Chapman, and R. C. Tyce, (1983). “A range-gated
laser system for ocean floor imaging,” Marine Technology Society Journal, vol. 17.

J. McLean and K. Voss, (1991).“Point spread functions in ocean water: comparison


[9]

between theory and experiment,” Applied Optics, vol. 30, pp. 2027–2030.

K. Voss, (1991). “Simple empirical model of the oceanic point spread function,”
[10]

Applied Optics, vol. 30, pp. 2647–2651.

J. Jaffe, K. Moore, J. McLean, and M. Strand, (2001). “Underwater optical imaging:


[11]

status and prospects,” Oceanography, vol. 14, pp. 66–76.

J. Mertens and F. Replogle, (1977). “Use of point spread and beam spread functions
[12]

for analysis of imaging systems in water,” Journal of the Optical Society of America, vol.
67, pp. 1105– 1117.

10

You might also like