Underwater Image Enhancement Method Based on Wavelet Transform and Retinex

Due to the complex underwater environment, the light will be scattered and absorbed in water, so the underwater image has problems such as poor contrast, blur, uneven illumination and so on. An underwater image enhancement method based on wavelet transform and Retinex algorithm is proposed. The algorithm consists of three main steps. Firstly, the image is converted into HSI color space, and the brightness component is preprocessed by Retinex algorithm. Then, the preprocessed brightness component was transformed by wavelet transform, and the low-frequency component was enhanced by contrast limited adaptive histogram equalization (CLAHE), and the high-frequency component was enhanced by logarithmic function. Finally, the enhanced image is obtained by inverse wavelet transform. The peak signal to noise ratio (PSNR) and structural similarity index (SSIM) were used as objective indexes to evaluate the enhanced underwater image, and the experimental results show that the algorithm can improve the quality of underwater image very well.