A survey on Visual Enhancement and Restoration of Sub-Aqua Image

Abstract: In Underwater Image processing, the basic physics of light propagation in the water medium comes into extinction. When light enters the water, it is exponentially attenuated, and so the visibility distance is limited. Underwater images suffer from blurring, non uniform lightening, noise, low contrast, etc. Therefore, underwater image processing is necessary. The filters used in the enhancement methods improve the image quality, suppress the noise, preserves the edges in an image and smoothen the image. Object recognition is done based on color, shape, background scenery, suspended particles and object features. The proposed technique comprises a combination of four filters such as homomorphic filtering, wavelet denoising, weiner filter and contrast equalization. These filters are applied sequentially on degraded underwater images. There are four different algorithms discussed with respect to this. The preprocessing technique comprises of homomorphic filtering to correct non-uniform illumination of light, wavelet denoising to remove additive Gaussian noise present in underwater images, weiner filtering to removes the blurred portion of the image and contrast stretching to normalize the RGB values. The proposed technique enhances the quality of the underwater images and can be employed prior to apply computer vision techniques.

Keywords: Homomorphic-Filter, Wavelet-Denoising, Bilateral-Filter, Histogram-Equalization, Color-Stretching, Polarizing-Filter, weiner filter.