Abstract Sand-dust color images suffer from poor image visibility and serious color cast that significantly affect the performance of outdoor computer vision systems. Therefore, this paper proposes an integrated enhancement method for the sand-dust image. The proposed method improves the image visibility and removes the sand-dust color cast. It integrates two main processes in two different color models. The adaptive gray world-blue channel (AGW-B) is utilized in the Red-Green-Blue (RGB) color model to remove the sand-dust color cast. Then, the contrast limited adaptive histogram equalization with normalized intensity and saturation correction (CLAHE-NISC) is conducted in a Hue-Saturation-Intensity (HSI) color model to enhance the image visibility. Sand-dust images with weak, medium, and extreme sand-dust color casts were utilized in the subjective and objective evaluations. Results show that the proposed method produced better and clearer enhanced images than the other four current sand-dust image enhancement methods.

Optimization algorithms are a key tool in image restoration. The Quadratic Penalty Alternating Minimization (QPAM) algorithm is an algorithm used to tackle image restoration challenges. However, the persistent challenge of slow convergence speed remains. Efforts have been made to enhance convergence speed, including extending the algorithm with Nesterov's momentum method. Yet, the algorithm displays oscillatory patterns during the minimization process, which may result in slow convergence speed. To address this issue, we proposed a conjugate gradient style momentum to accelerate the QPAM for image restoration. The iterative scheme of the proposed method consists of a proximal linearization that is re-formulated for the conjugate momentum acceleration. Experiments on both Gaussian and Poisson noise image restoration show that our proposed Conjugate Momentum QPAM is at par with or better than the original QPAM and its Nesterov-accelerated version in terms of CPU time.