Underwater image restoration with Haar wavelet transform and ensemble of triple correction algorithms using Bootstrap aggregation and random forests

This paper presents both a new strategy for traditional underwater image restoration using Haar wavelet transform as well as a new learned model that generates an ensemble of triple correction algorithm labels based on histogram quadrants’ cumulative distribution feature instead of generating pixel intensities. The Haar wavelet transform is our tentative dynamic stretching plan that is applied on the input image and its contrast stretched image to generate the degraded wavelet coefficients which are blended using Gaussian pyramid of the saliency weights to restore the original image. The ensemble of triple corrections exerts three color correction algorithms sequentially on the degraded image for restoration. The ensemble of algorithms entails the superposition effect of the red channel mean shifting, global RGB adaptation, global luminance adaptation, global saturation adaptation, luminance stretching, saturation stretching, contrast stretching, adaptive Gamma correction for red spectrum, even to odd middle intensity transference using look-up table, green to red spectrum transference using histogram equalization, local brightening, Dark Channel Prior, fusion restoration, and our Haar wavelet transform restoration. The source is available at https://github.com/vahidr213/Underwater-Image-Restoration-And-Enhancement-Collection.