Enhancing the low quality images using Unsupervised Colour Correction Method

Abstract

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 paper, we propose an Unsupervised Colour Correction Method (UCM) for underwater image enhancement. UCM 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 have been applied for contrast correction to increase the true colour using Saturation and to address the illumination problem through Intensity. We compare our results with three well known methods, namely Gray World, White Patch and Histogram Equalisation using Adobe Photoshop. The proposed method has produced better results than the existing methods.

Underwater image quality enhancement through composition of dual-intensity images and Rayleigh-stretching

“…However, it does not optimally increase the image contrast. Iqbal et al proposed the integrated color model (ICM) (Iqbal et al 2007) and the unsupervised color correction method (UCM) (Iqbal et al 2010). In Iqbal et al (2007), the output image in the red-green-blue (RGB) color model is stretched over the entire dynamic range.…”

“…After stretching, the image in HSI color model is then converted back into the RGB color model to produce an enhanced output image. In (Iqbal et al 2010), Iqbal et al modified two color channels, red and green, based on the Von Kries hypothesis to reduce the color cast. Contrast correction is then applied in the RGB color model.…”

“…Contrast stretching toward the upper side is applied to red, which is the lowest intensity channel. Contrast stretching at both sides is applied to green, which is the middle intensity value of the color channels, and contrast stretching at the lower side is applied to blue, which is the dominant color cast (Iqbal et al 2010). For underwater images, the image is further converted into the HSI color model, and the S and I components are stretched at both the lower and upper sides.…”

A Survey on Underwater Image Enhancement Techniques

“…[14] worked on "Enhancing the low quality images using Unsupervised Colour Correction Method,", The affected underwater images reduced contrast and non-uniform color cast because of the absorption and scattering of light rays in the marine environment. For that they proposed an Unsupervised Colour Correction Method (UCM) for underwater image quality enhancement.…”

Visibility in underwater robotics: Benchmarking and single image dehazing

“…The main drawback of this approach is it amplifies the noise in homogeneous regions and creates false colors. Some research lines work to palliate this problems like [Hitam et al, 2013], [Iqbal et al, 2010] and [Ghani and Isa, 2015] combining different histogram equalizations, target distributions and contrast stretching.…”