When dealing with outdoor hazy images, traditional image dehazing algorithms are often affected by the sky regions, resulting in appearing color distortions and detail loss in the restored image. Therefore, we proposed an optimized dark channel and haze-line priors method based on adaptive sky segmentation to improve the quality of dehazed images including sky areas. The proposed algorithm segmented the sky region of a hazy image by using the Gaussian fitting curve and prior information of sky color rules to calculate the adaptive threshold. Then, an optimized dark channel prior method was used to obtain the light distribution image of the sky region, and the haze-line prior method was utilized to calculate the transmission of the foreground region. Finally, a minimization function was designed to optimize the transmission, and the dehazed images were restored with the atmospheric scattering model. Experimental results demonstrated that the presented dehazing framework could preserve more details of the sky area as well as restore the color constancy of the image with better visual effects. Compared with other algorithms, the results of the proposed algorithm could achieve higher peak signal-to-noise ratio (PSNR) and structural similarity index (SSIM) evaluation values and provide the restored image with subjective visual effects closer to the real scene.
Since signal-dependent noise in a local weak texture region of a noisy image is approximated as additive noise, the corresponding noise parameters can be estimated from a given set of weakly textured image blocks. As a result, the meticulous selection of weakly textured image blocks plays a decisive role to estimate the noise parameters accurately. The existing methods consider the finite directions of the texture of image blocks or directly use the average value of an image block to select the weakly textured image block, which can result in errors. To overcome the drawbacks of the existing methods, this paper proposes a novel noise parameter estimation method using local binary cyclic jumping to aid in the selection of these weakly textured image blocks. The texture intensity of the image block is first defined by the cumulative average of the LBCJ information in the eight neighborhoods around the pixel, and, subsequently, the threshold is set for selecting weakly textured image blocks through texture intensity distribution of the image blocks and inverse binomial cumulative function. The experimental results reveal that the proposed method outperforms the existing alternative algorithms by 23% and 22% for the evaluative measures of MSE (a) and MSE (b), respectively.