Coarse-to-Fine Saliency Detection Based on Non-Subsampled Contourlet Transform Enhancement

Dongmei, 刘冬梅 Liu; Fa-liang, 常发亮 Chang

doi:10.3788/aos201939.0115003

Cited by 3 publications

(4 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Table 1 shows the quantitative evaluation of different defogging methods on the SOTS dataset. It can be seen that the quantitative evaluation metrics of the recovered results using [4,5] were low, while the quantitative evaluation metrics of the recovered results using these deep learning methods in [9,10] were improved to some extent. The algorithm in this paper was 6.36 and 0.08 higher than that in [9] in the PSNR and SSIM, respectively, and only below that in [15] in both the PSNR and SSIM.…”

Section: Experimental Results Of Synthesizing Uniform Haze Imagesmentioning

confidence: 99%

“…In order to verify the effect of the model in this paper on recovering real foggy images, four real outdoor foggy images were selected for the defogging experiments, and the experimental results are shown in Figure 7. There was overexposure in the sky region after the method in [4] for haze removal (e.g., panels 2 and 3 of Figure 7b) and more serious color bias in the processed images (e.g., panel 4 of Figure 7b). The defogged image of the method in [5] solved the defect of the method in [4], in which the halo appeared in the sky region, but the serious problem of color bias of the processed image remains unresolved (e.g., the fourth panel of Figure 7b).…”

Section: Experimental Results Of Real Haze Imagesmentioning

confidence: 99%

“…There was overexposure in the sky region after the method in [4] for haze removal (e.g., panels 2 and 3 of Figure 7b) and more serious color bias in the processed images (e.g., panel 4 of Figure 7b). The defogged image of the method in [5] solved the defect of the method in [4], in which the halo appeared in the sky region, but the serious problem of color bias of the processed image remains unresolved (e.g., the fourth panel of Figure 7b). The method in [9] had more fog residue after defogging the test images.…”

Section: Experimental Results Of Real Haze Imagesmentioning

confidence: 99%

“…This kind of method mainly achieves the purpose of defogging by enhancing the contrast and saturation of the image, but it cannot solve the problem of image defogging well because it does not analyze the essential cause of the image degradation in a foggy environment from the root. The main algorithms based on this method include histogram equalization [2], Retinex theory [3], the wavelet decomposition transformation method [4], etc. The second type is the image restoration method based on the physical model.…”

Section: Traditional Fog Removal Methodsmentioning

confidence: 99%

See 3 more Smart Citations

Image Dehazing Algorithm Based on Deep Learning Coupled Local and Global Features

Yuan

Zhang

et al. 2022

Applied Sciences

View full text Add to dashboard Cite

To address the problems that most convolutional neural network-based image defogging algorithm models capture incomplete global feature information and incomplete defogging, this paper proposes an end-to-end convolutional neural network and vision transformer hybrid image defogging algorithm. First, the shallow features of the haze image were extracted by a preprocessing module. Then, a symmetric network structure including a convolutional neural network (CNN) branch and a vision transformer branch was used to capture the local features and global features of the haze image, respectively. The mixed features were fused using convolutional layers to cover the global representation while retaining the local features. Finally, the features obtained by the encoder and decoder were fused to obtain richer feature information. The experimental results show that the proposed defogging algorithm achieved better defogging results in both the uniform and non-uniform haze datasets, solves the problems of dark and distorted colors after image defogging, and the recovered images are more natural for detail processing.

show abstract