Search

A shadow-removal algorithm based on cycle generative adversarial network is proposed. There are two networks in the proposed method. To increase the diversity of shadow images for improving the robustness in the shadow-removal process, the first network is used to add shadows in nonshadow images to increase the variation of training data. Then, the second network is trained for the shadow-removal task. Six different losses are calculated and combined in the loss function to increase the performance. Ablation experiments show that the resulting images suffer from some artifacts without any of the six losses in the loss function. The proposed method presents lower value of root-mean-squared error and the superior visual quality compared to the state-of-the-art image removal algorithms.© 2019 spie and is&t [doi: 10.1117/1.JEI.28.1.013034] [ABSTRACT FROM AUTHOR]

Image denoising algorithms often require their parameters to be adjusted according to the noise level. We propose a fast and reliable method for estimating image noise. The input image is assumed to be contaminated by an additive white Gaussian noise process. To exclude structures or details from contributing to the estimation of noise variance, a Sobel edge detection operator with a self-determined threshold is first applied to each image block. Then a filter operation, followed by an averaging of the convolutions over the selected blocks, provides a very accurate estimation of noise variance. We successfully combine the effectiveness of filter-based approaches with the efficiency of block-based approaches, and the simulated results demonstrate that the proposed method performs well for a variety of images over a large range of noise variances. Performance comparisons against other approaches are also provided. [ABSTRACT FROM AUTHOR]