Underwater Image Enhancement Using Integrated Contrast Correction And White Balance Methods
Loading...
Date
2009-03
Authors
Kashif Iqbal
Journal Title
Journal ISSN
Volume Title
Publisher
Abstract
The clarity of underwater images is degraded by light absorption, scattering
of light and turbidity of water. Due to this, underwater images are affected by bluish
colour cast, low contrast and reduced illumination. This thesis proposes two
approaches "Integrated Colour Model" (ICM) and "White Balance Adaptive
Approach" (WBA) to address factors affecting image clarity.
The ICM is based on colour balancing, contrast correction of RGB colour
model and contrast correction of HSI colour model. Firstly, the colour cast is
reduced by equalizing the colour values. Secondly, an enhancement to a contrast
correction method is applied to increase the Red colour by stretching red histogram
towards the maximum (i.e., right side), similarly the Blue colour is reduced by
stretching the blue histogram towards the minimum (i.e., left side). Thirdly, the
Saturation and Intensity components of the HSI colour model has been applied for
contrast correction to increase the true colour using Saturation and to address the
illumination problem through Intensity.
The WBA approach is based on contrast correction and white balance
algorithms. A new efficient process for colour cast adjustment is introduced which
relies on statistical calculations. This is performed by determining the colour cast,
calculating the intensity ratio between RGB components and correcting the affected
image by applying two gain factors (i.e., Red and Green).
Both the ICM and WBA models have been evaluated using the three wellknown
methods: Human Perception, Edge Detection and Histogram. The use of
three different methods ensures that the proposed models are comprehensively
evaluated. The proposed approaches: ICM and WBA are compared with the
established methods (i.e., Gray World, Histogram Equalisation and White Patch) and
the latest research methods. The results show that both the ICM and WBA have
outperformed against the established methods in terms of colour enhancement,
contrast and illumination.
The latest research methods: (i) use artificial illumination to capture clear
reference image; (ii) use predefine threshold values; (iii) involve computationally
intensive local and global enhancement process and; (iv) regenerate the absorbed
wavelength of light using known depth of the scene. In some cases, the latest
research methods have achieved better results due to the fact that they have used
additional information (i.e., artificial illumination, predefined threshold values and
reference image) but the use of such information can reduce the adaptability of the
methods. Additionally WBA shows significant results when applied to underwater
videos and land images.
Description
Keywords
The clarity of underwater images , is degraded by light absorption