Attention map-guided multi-scale haze removal method for industrial inspection system

Abstract

We present a new haze removal algorithm based on attention map-guided multi-scale image processing. The proposed method is based on the frequency-domain coefficient correction of a set of images followed by their fusion based on the Laplacian pyramid. A new stage is presented in obtaining a local-global estimate of high-contrast images, also used in the attention map-guided fusion model. The algorithm consists of the following steps: gamma correction with different gamma parameters; the weight map calculation by multiplying the saturation, contrast, and attention for each image; decomposition of the weight map into a Gaussian pyramid; 3-D block-rooting enhancement; decomposition of images after 3-D block-rooting and gamma correction into the Laplacian pyramid; merging by multiplying multi-scale images and weights. The experiment results on the dataset D-HAZE confirmed the high efficiency of the proposed enhancement method compared to the state-of-the-art techniques for industrial inspection systems.