Fast Image Enhancement Based on Color
Space Fusion
Jinsheng Xiao,
1,2
Hong Peng,
1
Yongqin Zhang,
3
*
Chaoping Tu,
1
Qingquan Li
2,4
1
School of Electronic Information, Wuhan University, Wuhan 430072, People’s Republic of China
2
State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan 430079, People’s Republic
of China
3
School of Information Science and Technology, Northwest University, Xi’an 710127, People’s Republic of China
4
President Office, Shenzhen University, Shenzhen 518060, People’s Republic of China
Received 29 April 2014; revised 17 October 2014; accepted 18 October 2014
Abstract: The current Retinex algorithm processes the
RGB channels separately for color image enhancement.
However, it changes the ratios of RGB components and
also causes some serious problems, such as color distor-
tion, color noise, and the halo artifacts. To solve these
issues, we propo se a novel algorithm based on color
space fusion. The single scale Retinex with fast mean fil-
tering is applied to the luminance component in hue-satu-
ration-value (HSV) color space. An enhancement
adjustment factor is introduced to avoid color distortio n
and noise amplification. Then, the surrounding function is
replaced by a small scale Gaussian filter in RGB color
space to eliminate the halo artifact. A parameter is
involved to keep the color natural when the reflection is
estimated. Finally, the enhanced color image is con-
structed from the weighted averaging results of these two
steps. The subjective and objective evaluations of many
different backlight images captured by different cameras
are implemented to verify the validity of the proposed
algorithm in our experiments. The experimental results
show that the proposed algorithm can not only signifi-
cantly suppress the halo effect and noise amplification,
but can also remove color distortion. Our proposed algo-
rithm is superior to the multi-scale Retinex with color
restoration approach and other state-of-the-art methods.
V
C
2014 Wiley Periodicals, Inc. Col Res Appl, 41, 22–31, 2016; Pub-
lished Online 19 November 2014 in Wiley Online Library (wileyonline-
library.com). DOI 10.1002/col.21931
Key words: color image enhancement; Retinex theory;
multi-scale Retinex with color restoration; halo artifact
INTRODUCTION
Color image enhancement has been widely used in the
fields of medical imaging, industrial inspection, and geo-
morphology in recent years.
1
Its task is to get finer details
of an image and highlight the useful information.
2
When
an image is captured by a digital camera or a mobile ter-
minal, the illumination tends to be irregular and uncon-
trolled under the certain light sources, such as sun light
or street lamps in the open air or fluorescent lamps in a
room. These cases lead to image degradation in that there
exist excessively bright or dark regions of the captured
images in part.
After a brief review, according to the processing
domain, the image enhancement can be mainly divided
into two groups: spatial domain processing techniques
and transform domain processing techniques. In the first
group, the Retinex theory simulates the human visual cor-
tex and presents a simplified model. Land
3
systematically
put forward the Retinex model, and applied it to image
enhancement. In the 1990s, Jobson et al.
4
proposed the
single scale Retinex (SSR) algorithm which uses the cen-
ter surround method to estimate illuminate component of
a pixel by its neighbors. The SSR algorithm uses the
weighted average to replace the center pixel within a
scale. But it is difficult to guarantee both the color fidelity
*Correspondence to: Yongqin Zhang (e-mail: zhangyongqin@pku.edu.cn)
Contract grant sponsor: National Natural Science Foundation of China; con-
tract grant numbers: 91120002, 61471272, 61201442.
V
C
2014 Wiley Periodicals, Inc.
22 COLOR research and application