VOL.8 NO.

1March 2019 - ISSN 2233 – 1859

Southeast Europe Journal of Soft Computing

Available online: http://scjournal.ius.edu.ba

A Review on Image Enhancement Techniques

Haris Ačkar, Ali Abd Almisreb Mohamed A. Saleh

Faculty of Engineering and Natural Sciences, Faculty of Electrical Engineering,
International University of Sarajevo, Universiti Teknologi MARA (UiTM),
Hrasnicka cesta
esta 15, Ilidža 71210 Sarajevo, Malaysia
Bosnia and Herzegovina
[email protected]

Article Info Abstract

Article history: Image Enhancement is one of the most important and complex techniques
in image processing technology. The main aim of image enhancement is
Article received on 13 January 2018 to improve the visual appearance on an image and to offer a better
Received in revised form 25
February2018 representation of the image for Computer Vision Algorithms. In this
paper,we is covered a few application fields of image enhancement with
various images like grayscale, color, infrared and even with videos. The
main objective of this paper is to highlight the drawbacks of the state of
Keywords: the art image enhancement techniques.
Enhancement;underwater images,
medical images, deffoging
algorithms, infrared images,
heuristic methods.

1. INTRODUCTION image enhancement. In this paper will be presented state of

the art techniques for image enhancement of grayscale and
Image enhancement is one of the preprocessing steps in color images. A short description of those methods will be
various computer vision applications. It is the process of provided and their field of application. Every Computer
improving the quality of the image without any information
info Vision algorithm requires high-visibility
visibility input images in
loss. For example in medical images [1], contrast order to produce some output. However, in most situations,
enhancement is mostly used for increasing the quality of images are taken in some specific conditions like low
low-light.
any image. The basic importance of the contrast Therefore, we need to enhance those images before further
enhancement is to improve the pixel brightness in medical processing in order to have correct results from Computer
application. A lot of methods are introduced
ntroduced in research Vision algorithms. In general, image enhancement
enhan methods
papers, and every method has one or few application fields. need to „correct“ input images for specific purpose so that
Depend on the field application, types of images, grayscale those images can be more suitable for specific Computer
or color images, we need to choose the proper method for Vision Algorithms.
43 H. Ackar et al./ Southeast Europe Journal of Soft Computing Vol.8 No.1 March 2019 (42-48)

This paper is organized into 8 sections, Section 1 gives papers describe the development of improved fuzzy rule-
an overview of the paper. It describes the importance of based edge detection technique.
image enhancement in image processing. Section 2 gives a
literature review for image enhancement techniques for 4. VIDEO AND IMAGE DEFOGGING
underwater images. Section 3 gives a literature review for ALGORITHMS
image enhancement techniques for medical images. Section
4 gives a short review of video and image defogging
Videos and images acquired by a visual system are
algorithms. Section 5 gives an overview of techniques for
seriously degraded under hazy and foggy weather, which
infrared image enhancement and sections 6 gives a
will affect the detection, tracking, and recognition of
literature review for contrast enhancement. Section 7 gives
targets. In that purpose a lot of video and image defogging
a short review of Haze visibility enhancement of images.
algorithms is created. The images acquired by the camera
Section 8 gives a short review of latest image enhancement
in foggy and hazy weather is degraded and usually has low
techniques from 2018 and 2019.
contrast and poor visibility [18]. Some of the interesting
fields of application for image defogging algorithms are to
2. IMAGE ENHANCEMENT TECHNIQUES enhance the visibility of the vehicle visual system, which
FOR UNDERWATER IMAGES can effectively prevent car accidents [19]. Some papers use
a physical imaging model based on the atmospheric
Underwater images are corrupted due to scatters and scattering phenomenon for image defogging [20, 21]. Many
amalgamation, resulting in low contrast and color distortion improved defogging algorithms for unmanned surface
[2]. There are many image enhancement techniques such as vehicle visual system are based on the physical model for
white balance, color correction, histogram equalization, and outdoor scenes [22-26]. In past years, some institutions
fusion-based methods [3]. Various image enhancement have done research on image defogging and obtained good
techniques can be found in the literature. Hue variations can results. NASA has studied the image enhancement and
be minimized by wavelength compensation [4]. Also, defogging algorithm since 1995, and their research has
underwater images have low perceivability, small made a great contribution to the field of image
divergence and lessening hues [5]. To enhance underwater enhancement based on the Retinex theory. Their algorithms
images, some authors propose unsupervised digital image can greatly enhance the visibility of an image acquired
color equalization [6]. Other authors use histogram under bad weather conditions, such as smoke, haze,
modifications techniques to increase the quality of underwater, night or low illumination conditions [26-30].
underwater image [7, 8], and there are also researchers who
purposes algorithms to reduce underwater perturbations and 5. IMAGE ENHANCEMENT OF INFRARED
to improves image quality [9, 10]. IMAGES
3. IMAGE ENHANCEMENT TECHNIQUES In this section, it will be provided a survey of
FOR MEDICAL IMAGES enhancement of infrared images with two spatial and
spatiotemporal homomorphic filtering algorithms based on
In the medical images, the main role plays contrast infrared imaging model. The Wavelength of infrared light
enhancement to increase the quality of an image [11]. Edge is longer than of visible light, the visible red light has
detection is also playing an important role in medical wavelength of 0.74 micrometers at the end of visible
imaging because all information has preserved in edges. In spectrum, infrared light has 300 micrometers wide
literature can be found a lot of interesting image wavelength band startng from 0.74 micrometers. These
enhancement techniques for medical devices, classic but wavelengths correspond to a frequency range of
also and fuzzy approaches. Some researchers propose fuzzy approximately 1 to 400 THz [31]. Spatial and
hyperbolization to increase the clarity of the image [12]. spatiotemporal homomorphic filtering algorithms are
There are also techniques for medical images using type-II designed. The spatiotemporal homomorphic filter uses the
fuzzy set [13]. The detailed description of type-II fuzzy set temporal information provided by the image sequence so
can be found in [14]. Survey paper like [15] presenting a that an enhancement is faster than that obtained by utilizing
detailed overview of image enhancement using fuzzy the spatial homomorphic filtering. STHF will spend less
techniques. The main advantage of those techniques is to time and iterations to compute a resulting image from a
enhance the contrast and improve the quality of the image. similar degree of convergences the enhance images are in
A lot of authors are proposing various medical image general not good as those from SHF. Some authors suggest
enhancement techniques using type-II fuzzy approach. The using Wavelets for edge detection and as approximate
[15] proposes type-II fuzzy computing techniques for matched filters. Wavelets as edge detectors assume that
image enhancement. The [16] proposes Edge detection target edges on image differ in some way from clutter
method based on type-II fuzzy system for color images. At edges [32, 33]. In some cases, a priori knowledge of target
the end, papers like [17] can be found in literature, those is important in order to do scale separation [34]. Also,
44 H. Ackar et al./ Southeast Europe Journal of Soft Computing Vol.8 No.1 March 2019 (42-48)

wavelets can be designed to function as approximate absorbing and scattering light in the enviroment, because of
matched filters [35]. this scattering and absorption we have degradation in hazy
images. This scattering and absorption reduce the direct
6. CONTRASTENHANCEMENT transmission of the light from the scene to the camera. The
TECHNIQUES attenuated direct transmission causes the intensity from the
scene to be weaker, while the airlight causes the appearance
of the scene to be washed out [42]. The one of the earliest
Contrast is the visual difference that makes an object
methods to analyze images of scenes captured in scattering
distinguishable from the background and other objects.
media is to extract scene depth by exploiting the presence
Contranst enhancement techniques are changing pixel
of the atmospheric scattering effects [43]. The methods
intensitiy of the input imate in order to utilize maximum
proposed in [44] does not assume that the haze-free image
possible bins. It has been an active research topic since the
is provided. These two methods are pioneers in dealing
early days of computer vision and digital image processing.
with atmospheric particles. Some methods for haze
In this section, the focus will be on contrast enhancement
enhancement uses different base for enhancement like
techniques for effective contrast enhancement. Most of the
multiple images, polarizing filters, known depth and single-
researchers are focused on histogram-based contrast
image. The multiple images methods uses multiple images
enhancement techniques. Histogram based techniques, like
of same scene taken in different hazy conditions. With the
Homomorphic Filtering, are used to enhance the low
assumption that images are taken from the same scene, they
contrast for medical images [36]. In the literature can be
are sharing same color of atmospheric light but they have a
found modified versions of the hyperbolic algorithm for
different direct transmission of colors. From this two planes
contrast enhancement. These modified algorithm are
can be formed in the RGB space that intersect each other.
suitable for enhancement of magnetic resonance images.
In [45] is presented how to estimate the atmospheric light
This technique uses controlled fashion of the gray level
sith this intersect, which is similar to [46] for estimating a
which is streching on whole image [37]. There are also
light color from specular reflection. For methods with
contrast enhancement techniques based on Fuzzy
known depth is proposed several algorithms based on a
techniques. Fuzzy techniques can manage imperfectness of
single input image and they requires some user interaction
an image modeled as the uncertainty in the image. Fuzzy
[47]. The first method from this paper requires from user to
method for contrast enhancement can be divided into three
select a region with less haze and region with more haze of
stages, like classic fuzzy system: fuzzification, modification
the same reflection as the first one's. From these inputs,
of membership functions and defuzzification of the image
proposed algorithm can calculate resulting image and
[38]. In the literature can be found an automatic methods
dehaze hazy pixels. The second method asks user to
for contrast enhancement. For example, by grouping the
indicate vanishing point and to input the maximum and
histogram components of a low-contrast image into a
minimum distance from the camera. This information is
proper number of bins according to a selected criterion,
used to interpolate the distance to estiamte the clear secene
then redistribute these bins uniformly over the grayscale.
between. In the paper [48] is proposed a framework for
The last step is to ungroup the previously grouped gray-
contrast enhnacement of images taken in a vehicle.
levels. This technique is known as gray-level grouping
(GLG) [39, 40]. Some authors propose an extension of
histogram equalization. With this approach, it is possible to 8. LATEST IMAGE ENHANCEMENT
have independent histogram equalizations for two sub- TECHNIQUES
images found by decomposing the input image based on its
mean value. Resulting equalized sub-images are bounded The latest image enhnacement technques can be
by each other around the input mean. This approach has a devided into two groups, heuristic and classic image
great geature, it maintains the mean brightness of given enhancement techniques. In first part of this chapter, it will
input images significantly [41]. be given review about novel classic image enhancement
techniques and after that it will be given review about
7. VII. HAZE VISIBILITY heuristic image enhancement techniques. One of the latest
ENHANCEMENT OF IMAGES classic algorithms for contours detectin in thermal images is
based on theory of sampling Kantorovich operators and on
analysis of the histogram of the enhanced thermographic
The haze is the most common real-world
image [49]. Contrast Enhancement is an important step for
phenomena caused by atmospheric particles. Images
the analysis of microscopy images. In paper [50] is
captured in hazy scenes suffers from visibility degradation
proposed groundbrakeing design of the Phase Contrast
and significant reduction of contrast. Recovering scenes
Microscopy Framework. The proposed image enhnacement
from hazy images can be critical for image processing and
framework transforms the changes in image phase into the
computer vision algorithms. Algorithms for haze-free
variations of magnitude to enhance the structural details of
photographs are developed because consumers want a clear
the image and to improve visibility. In paper [51] is
visual content when they are shooting target objects or
proposed algorithm for image enhancing approach for
landscapes. The floating particles in the atmosphere are
transforming dark images into lightened scenes. This
45 H. Ackar et al./ Southeast Europe Journal of Soft Computing Vol.8 No.1 March 2019 (42-48)

approach uses classical color transfer method to obtain first considered as an optimization problem and the artificial bee
order statistics from a target image and transfer them to a colony algorithm is utilized to find the optimal solution for
dark input by modifying its hue and brightness. This this optimization problem. In the paper [65] can be found a
method can be used as a preprocessing step in order to survay on Nature-Inspired optimization algorithms and
improve the recognition and interpretation of dark imagery their application in image enhancement domain. Single
in a wide range of applications. Remote sensing images image contrast enhancement methods are used to adjust the
often suffer low contrast, and the efficiency and robustness tone curve to correct the contrast of an input image. In the
of contrast enhancement. In the paper [52] is proposed paper [66] is proposed learning algorithm of convolutional
improved adaptive contrast enhancement method based on neural network to train a single image contrast enhancer. In
histogram compacting transform. In the papers [53, 54] are the paper [67] is proposed a deep learning neural network
presented low-lightning image enhancement based on with purpose of obtaining enhanced representations of the
Retinex model. The different Retinex models are proposed sequences for visual odometry. After initial results, it is
in order to enhance illumination and reflectance. New proposed a reduced size of convolutional neural network
image enhnacement method based on Nonsubsampled for faster computation. In the paper [68] is propsoed
Contourlet Transform is proposed in paper [55]. In this Learned Perceptual Image Enhancement technique. The
paper is presented contourlet transform as an extension of two main contributions of this paper are presenting state of
the wavelet transform that provides a multi-resolution and the art predictor that encompasses several aspects of human
multi-direction analysis for two dimensional images. In perceptual preferences and the researchers uses neural
the paper [56] is presented a high-resolution image image asessment as a perceptual loss for image
enhancement wavelet-based algorithm for edge smoothness enhancement tasks.
of an Satelite Image. The proposed algorithm apply the
three-level discrete wavelet transform and compute the 9. CONCLUSION
output of the algorithm. In order to improve contrast and
restore color for underwater images without suffering from Image enhancement techniques change images to
insufficient details and color cast, in the paper [57] is provide a better representation of the information
proposed a fusion algorithm for different color spaces based encapsulated in the image. In this paper is presented a
on contrast limited adaptive histogram equalization. review for various fields of image enhancement. For every
In order to have an effective colour enhancement purpose like underwater imaging or medical images, there
framework for statistical and logarithmic image processing are different algorithms and techniques suitable for image
enhancement algorithms, the paper [58] proposes approach enhancement. As we can see from this review paper, and
of utilizing the fusion of partial, multiple computed also from other review papers, there is no universal image
luminance channels with colour image channel statistics enhancement technique, the most important reason for that
obtained from the input colour image for adaptive color is the fact that there are a lot of different factors, for
enhancement. The Unmanned Aerial Vehicles are widely example, fogg in images and videos, or the fact that
used for capturing images in border area surveillance, medical images are mostly grayscale images.
disaster intensity monitoring, etc. In the paper [59] is
presented usage of Firefly Algorithm in order to enhance REFERENCES
aerial images taken by a Mini Unmanned Aerial Vehicle
via optimizing the value of certain parameters. For Smart [1] Rana, S. B., & Rana, S. B. (2015). A Review of
City applications it is crucial to have a good pre-processing Medical Image Enhancement Techniques for
technique for infrared image enhancement. Existing Image Processing. International Journal of Current
grayscale mapping-based algorithms always suffer from Engineering and Technology, 5(2), 1282-1286.
over-enhancement of the background, noise amplicifation [2] Sandbhor, B., & Kharat, G. U. (2015). A review
and brightness distortion. In the paper [60] is proposed an on Underwater Image Enhancement Techniques.
adaptive histogram partition and brightness correction in Int. J. Advanced Research in Computer Science
order to correct above mentioned problems. and Software Engineering, 5(5), 676-680.
In the paper [61] are proposed two novel [3] Ancuti, C., Ancuti, C. O., Haber, T., & Bekaert, P.
histogram based image enhancement algorithms. The (2012, June). Enhancing underwater images and
proposed algorithms provide the way to control the videos by fusion. In 2012 IEEE Conference on
brightness and contrast of enhanced image by adjusting the Computer Vision and Pattern Recognition (pp. 81-
parameters. After classic image enhancement techniques, 88). IEEE.
the novel huristic methods will be described. Low-light is a [4] Sathya, R., & Bharathi, M. (2015). Enhancement
challenging enviroment for image processing. In the paper of Underwater Images Using Wavelength
[62] is proposed method for low-light image enhancement Compensation Method. International Journal of
using Gaussian Process and Convolutional Neural Network. Innovative Research in Computer and
In the papers [63, 64] are proposed image enhancement Communication Engineering, 3(3), 1829-1835.
techniques using biologically inspired artificial Bee Colony [5] Talwar, S., & Kochher, R. (2015). Evaluation of
Algorithms. In this papers image constrast enhnacement is Underwater Image Dehazing Techniques.
46 H. Ackar et al./ Southeast Europe Journal of Soft Computing Vol.8 No.1 March 2019 (42-48)

International Journal for Science and Emerging Conference on Computer Vision and Pattern
Technologies with Latest Trends, 21(1), 11-13. Recognition (pp. 1-8). IEEE.
[6] Rizzi, A., Gatta, C., & Marini, D. (2003). A new [20] Narasimhan, S. G., & Nayar, S. K. (2002). Vision
algorithm for unsupervised global and local color and the atmosphere. International journal of
correction. Pattern Recognition Letters, 24(11), computer vision, 48(3), 233-254.
1663-1677. [21] Narasimhan, S. G., & Nayar, S. K. (2001,
[7] Iqbal, K., Salam, R. A., Osman, A., & Talib, A. Z. December). Removing weather effects from
(2007). Underwater Image Enhancement Using an monochrome images. In IEEE computer society
Integrated Colour Model. IAENG International conference on computer vision and pattern
Journal of Computer Science, 34(2). recognition (Vol. 2, pp. II-186). IEEE Computer
[8] Iqbal, K., Odetayo, M., James, A., Salam, R. A., & Society; 1999.
Talib, A. Z. H. (2010, October). Enhancing the [22] John, J., & Wilscy, M. (2008, September).
low quality images using unsupervised colour Enhancement of weather degraded video
correction method. In 2010 IEEE International sequences using wavelet fusion. In 2008 7th IEEE
Conference on Systems, Man and Cybernetics (pp. International Conference on Cybernetic Intelligent
1703-1709). IEEE. Systems (pp. 1-6). IEEE.
[9] Bazeille, S., Quidu, I., Jaulin, L., & Malkasse, J. P. [23] Ramya, C., & Rani, D. S. S. (2012). Contrast
(2006, October). Automatic underwater image pre- enhancement for fog degraded video sequences
processing. In CMM'06 (p. xx). using BPDFHE. Int. J. Comput. Sci. Inf. Technol,
[10] Bazeille, S. (2008). Vision sous-marine 3(2), 3463-3468.
monoculaire pour la reconnaissance d'objets [24] Xu, Z., Liu, X., & Chen, X. (2009, December).
(Doctoral dissertation, Brest). Fog removal from video sequences using contrast
[11] Kaur, R., Chawla, M., Khiva, N. K., & Ansari, M. limited adaptive histogram equalization. In 2009
D. (2017). On Contrast Enhancement Techniques International Conference on Computational
for Medical Images with Edge Detection: A Intelligence and Software Engineering (pp. 1-4).
Comparative Analysis. Journal of IEEE.
Telecommunication, Electronic and Computer [25] Lin, Z., & Wang, X. (2012). Dehazing for image
Engineering (JTEC), 9(3-6), 35-40. and video using guided filter. Appl. Sci, 2, 123-
[12] Hartati, S., Harjoko, A., & Nickerson, B. G. 127.
(2009). Fuzzy hyperbolization image enhancement [26] SINGH RAJPUT, G., & RAHMAN, Z. U. (2008).
and artificial neural network for anomaly Hazard Detection on Runways using Image
detection. processing Techniques. In Proceedings of SPIE,
[13] Chaira, T. (2012). A rank ordered filter for medical the International Society for Optical Engineering
image edge enhancement and detection using (pp. 69570D-1). Society of Photo-Optical
intuitionistic fuzzy set. Applied soft computing, Instrumentation Engineers.
12(4), 1259-1266. [27] Jobson, D. J., Rahman, Z. U., & Woodell, G. A.
[14] Karnik, N. N., Mendel, J. M., & Liang, Q. (1999). (1996, January). Retinex image processing:
Type-2 fuzzy logic systems. IEEE transactions on Improved fidelity to direct visual observation. In
Fuzzy Systems, 7(6), 643-658. Color and Imaging Conference (Vol. 1996, No. 1,
[15] Sesadri, U., & Nagaraju, C. (2015). TYPE2 pp. 124-125). Society for Imaging Science and
FUZZY SOFT COMPUTING TECHNIQUE FOR Technology.
IMAGE ENHANCEMENT. International Journal [28] Rahman, Z. U., Jobson, D. J., & Woodell, G. A.
of Computer Science and Information Security, (1996, November). Multiscale retinex for color
13(11), 94. rendition and dynamic range compression. In
[16] Ansari, M. D., Ghrera, S. P., & Tyagi, V. (2014). Applications of Digital Image Processing XIX
Pixel-based image forgery detection: A review. (Vol. 2847, pp. 183-192). International Society for
IETE journal of education, 55(1), 40-46. Optics and Photonics.
[17] Ansari, M. D., & Ghrera, S. P. (2018). [29] Rahman, Z. U., Woodell, G. A., & Jobson, D. J.
Intuitionistic fuzzy local binary pattern for features (1997). A comparison of the multiscale retinex
extraction. International Journal of Information with other image enhancement techniques.
and Communication Technology, 13(1), 83-98. [30] Rahman, Z. U., Jobson, D. J., Woodell, G. A., &
[18] Sharma, R., & Chopra, V. (2014). A review on Hines, G. D. (2005, September). Image
different image dehazing methods. International enhancement, image quality, and noise. In
Journal of Computer Engineering and Photonic Devices and Algorithms for Computing
Applications, 6(3). VII (Vol. 5907, p. 59070N). International Society
[19] Hautière, N., Tarel, J. P., & Aubert, D. (2007, for Optics and Photonics.
June). Towards fog-free in-vehicle vision systems [31] Qi, H., & Head, J. F. (2001). Asymmetry analysis
through contrast restoration. In 2007 IEEE using automatic segmentation and classification
47 H. Ackar et al./ Southeast Europe Journal of Soft Computing Vol.8 No.1 March 2019 (42-48)

for breast cancer detection in thermograms. In brightness preserving bi-histogram equalization.

2001 Conference Proceedings of the 23rd Annual IEEE transactions on Consumer Electronics, 43(1),
International Conference of the IEEE Engineering 1-8.
in Medicine and Biology Society (Vol. 3, pp. [42] Li, Y., You, S., Brown, M. S., & Tan, R. T.
2866-2869). IEEE. (2017). Haze visibility enhancement: A survey and
[32] Kuruganti, P. T., & Qi, H. (2002). Asymmetry quantitative benchmarking. Computer Vision and
analysis in breast cancer detection using thermal Image Understanding, 165, 1-16.
infrared images. In Proceedings of the Second [43] Cozman, F., & Krotkov, E. (1997, June). Depth
Joint 24th Annual Conference and the Annual Fall from scattering. In cvpr (Vol. 31, pp. 801-806).
Meeting of the Biomedical Engineering [44] Nayar, S. K., & Narasimhan, S. G. (1999). Vision
Society][Engineering in Medicine and Biology in bad weather. In Proceedings of the Seventh
(Vol. 2, pp. 1155-1156). IEEE. IEEE International Conference on Computer
[33] Scales, N., Kerry, C., & Prize, M. (2004, Vision (Vol. 2, pp. 820-827). IEEE.
September). Automated image segmentation for [45] Narasimhan, S. G., & Nayar, S. K. (2000).
breast analysis using infrared images. In The 26th Chromatic framework for vision in bad weather. In
Annual International Conference of the IEEE Proceedings IEEE Conference on Computer
Engineering in Medicine and Biology Society Vision and Pattern Recognition. CVPR 2000 (Cat.
(Vol. 1, pp. 1737-1740). IEEE. No. PR00662) (Vol. 1, pp. 598-605). IEEE.
[34] Zhang, C. J., Yang, F., Wang, X. D., & Zhang, H. [46] Tominaga, S., & Wandell, B. A. (1989). Standard
R. (2005, August). An efficient non-linear surface-reflectance model and illuminant
algorithm for contrast enhancement of infrared estimation. JOSA A, 6(4), 576-584.
image. In 2005 International Conference on [47] Narasimhan, S. G., & Nayar, S. K. (2003,
Machine Learning and Cybernetics (Vol. 8, pp. October). Interactive (de) weathering of an image
4946-4951). IEEE. using physical models. In IEEE Workshop on
[35] Andreone, L., Antonello, P. C., Bertozzi, M., color and photometric Methods in computer
Broggi, A., Fascioli, A., & Ranzato, D. (2002, Vision (Vol. 6, No. 6.4, p. 1). France.
September). Vehicle detection and localization in [48] Hautière, N., Tarel, J. P., & Aubert, D. (2007,
infra-red images. In Proceedings. The IEEE 5th June). Towards fog-free in-vehicle vision systems
International Conference on Intelligent through contrast restoration. In 2007 IEEE
Transportation Systems (pp. 141-146). IEEE. Conference on Computer Vision and Pattern
[36] Agarwal, T. K., Tiwari, M., & Lamba, S. S. (2014, Recognition (pp. 1-8). IEEE.
February). Modified histogram based contrast [49] Asdrubali, F., Baldinelli, G., Bianchi, F.,
enhancement using homomorphic filtering for Costarelli, D., Rotili, A., Seracini, M., & Vinti, G.
medical images. In 2014 IEEE International (2018). Detection of thermal bridges from
Advance Computing Conference (IACC) (pp. 964- thermographic images by means of image
968). IEEE. processing approximation algorithms. Applied
[37] Chong, S. S., Sim, K. S., & Nia, M. E. (2013, Mathematics and Computation, 317, 160-171.
October). Modified HL contrast enhancement [50] Cakir, S., Kahraman, D. C., Cetin-Atalay, R., &
technique for breast MR images. In 2013 IEEE Cetin, A. E. (2018). Contrast enhancement of
International Conference on Signal and Image microscopy images using image phase
Processing Applications (pp. 360-364). IEEE. information. IEEE Access, 6, 3839-3850.
[38] Mahashwari, T., & Asthana, A. (2013). Image [51] Cepeda-Negrete, J., Sanchez-Yanez, R. E., Correa-
enhancement using fuzzy technique. International Tome, F. E., & Lizarraga-Morales, R. A. (2018).
Journal of Research in Engineering Science and Dark image enhancement using perceptual color
Technology, 2(2), 1-4. transfer. IEEE Access, 6, 14935-14945.
[39] Chen, Z., Abidi, B. R., Page, D. L., & Abidi, M. A. [52] Chen, J., Liu, J., Zhou, C., Zhu, F., Chen, T., &
(2006). Gray-level grouping (GLG): an automatic Zhang, H. (2018, August). An automatic image
method for optimized image contrast enhancement method based on the improved
Enhancement-part I: the basic method. IEEE HCTLS. In 2018 10th IAPR Workshop on Pattern
transactions on image processing, 15(8), 2290- Recognition in Remote Sensing (PRRS) (pp. 1-6).
2302. IEEE.
[40] Chen, Z., Abidi, B. R., Page, D. L., & Abidi, M. A. [53] Gao, Y., Hu, H. M., Li, B., & Guo, Q. (2018).
(2006). Gray-level grouping (GLG): an automatic Naturalness preserved nonuniform illumination
method for optimized image contrast estimation for image enhancement based on
enhancement-part II: the variations. IEEE retinex. IEEE Transactions on Multimedia, 20(2),
Transactions on Image Processing, 15(8), 2303- 335-344.
2314. [54] Li, M., Liu, J., Yang, W., Sun, X., & Guo, Z.
[41] Kim, Y. T. (1997). Contrast enhancement using (2018). Structure-revealing low-light image
48 H. Ackar et al./ Southeast Europe Journal of Soft Computing Vol.8 No.1 March 2019 (42-48)

enhancement via robust Retinex model. IEEE Neurocomputing, 275, 2798-2809.

Transactions on Image Processing, 27(6), 2828- [62] Loh, Y. P., Liang, X., & Chan, C. S. (2019). Low-
2841. light image enhancement using Gaussian Process
[55] Hossain, M. F., Alsharif, M. R., & Yamashita, K. for features retrieval. Signal Processing: Image
(2010, June). A New Image Enhancement Method Communication, 74, 175-190.
Based on Nonsubsampled Contourlet Transform. [63] Ahmad, R., & Choubey, N. S. (2018). Review on
In International Conference on Advanced image enhancement techniques using biologically
Communication and Networking (pp. 74-80). inspired artificial bee colony algorithms and its
Springer, Berlin, Heidelberg. variants. In Biologically Rationalized Computing
[56] Sivakumar, R., & Mohan, E. (2018). High Techniques for Image Processing Applications
Resolution Satellite Image Enhancement Using (pp. 249-271). Springer, Cham.
Discrete Wavelet Transform. International Journal [64] Chen, J., Yu, W., Tian, J., Chen, L., & Zhou, Z.
of Applied Engineering Research, 13(11), 9811- (2018). Image contrast enhancement using an
9815. artificial bee colony algorithm. Swarm and
[57] Ma, J., Fan, X., Yang, S. X., Zhang, X., & Zhu, X. Evolutionary Computation, 38, 287-294.
(2018). Contrast limited adaptive histogram [65] Dhal, K. G., Ray, S., Das, A., & Das, S. (2018). A
equalization-based fusion in YIQ and HSI color Survey on Nature-Inspired Optimization
spaces for underwater image enhancement. Algorithms and Their Application in Image
International Journal of Pattern Recognition and Enhancement Domain. Archives of Computational
Artificial Intelligence, 32(07), 1854018. Methods in Engineering, 1-32.
[58] Nnolim, U. A. (2018). An adaptive RGB colour [66] Cai, J., Gu, S., & Zhang, L. (2018). Learning a
enhancement formulation for logarithmic image deep single image contrast enhancer from multi-
processing-based algorithms. Optik, 154, 192-215. exposure images. IEEE Transactions on Image
[59] Samanta, S., Mukherjee, A., Ashour, A. S., Dey, Processing, 27(4), 2049-2062.
N., Tavares, J. M. R., Abdessalem Karâa, W. B., ... [67] Gomez-Ojeda, R., Zhang, Z., Gonzalez-Jimenez,
& Hassanien, A. E. (2018). Log transform based J., & Scaramuzza, D. (2018, May). Learning-based
optimal image enhancement using firefly image enhancement for visual odometry in
algorithm for autonomous mini unmanned aerial challenging HDR environments. In 2018 IEEE
vehicle: An application of aerial photography. International Conference on Robotics and
International Journal of Image and Graphics, Automation (ICRA) (pp. 805-811). IEEE.
18(04), 1850019. [68] Talebi, H., & Milanfar, P. (2018, May). Learned
[60] Wan, M., Gu, G., Qian, W., Ren, K., Chen, Q., & perceptual image enhancement. In 2018 IEEE
Maldague, X. (2018). Infrared image enhancement International Conference on Computational
using adaptive histogram partition and brightness Photography (ICCP) (pp. 1-13). IEEE.
correction. Remote Sensing, 10(5), 682.
[61] Xiao, B., Tang, H., Jiang, Y., Li, W., & Wang, G.
(2018). Brightness and contrast controllable image
enhancement based on histogram specification.
 26 H. Ackar et al./ Southeast Europe Journal of Soft Computing Vol.8 No.1 March 2019 (42-48)

View publication stats