Fig 1.
Visual comparative analysis of images taken of underwater objects, our method highlights the realism of the object more, restores the initial color of the object, and the contrast and visibility are stronger than other methods, comparing methods either have blurred edges of the object or distorted colors.
Fig 2.
A framework diagram of our approach.
Framework diagram of our method. In our method, the input image is firstly added with image processing for color and contrast correction, the obtained result is then put into the visibility enhancement module based on type II fuzzy set for enhancement and adjustable contrast stretching module for adjustment respectively, the two output images obtained are finally fused by the visual fusion module to get the final output result.
Fig 3.
The input image is computed at each stage and finally the enhanced image is output.
Fig 4.
Validation results of the selected methods on the Test-C60 dataset are shown.
In this section we have arbitrarily selected three examples from the Test-C60 dataset.
Table 1.
Calculation of indicators obtained from the validation of different methods on the Test-C60 dataset. The best results are in red and the next best results are in blue.
Fig 5.
Validation results of the selected methods on the Test-C45 dataset are shown.
In this section we have randomly selected three examples from the Test-C45 dataset.
Table 2.
Calculation of indicators obtained from the validation of different methods on the Test-U45dataset. The best results are in red and the next best results are in blue.
Table 3.
Evaluation Metrics Results From The Missing Type-II Fuzzy Set Visibility Enhancement Module Ablation Experiment On The Test-C60 dataset.
Table 4.
Evaluation Metrics Results From The Missing Type-II Fuzzy Set Visibility Enhancement Module Ablation Experiment On the Test-U45 Dataset.
Fig 6.
Presentation of the results of the ablation experiment.
Fig 7.
Test results of 16 methods in edge detection.
Fig 8.
Test results of 16 methods in target detection.
Fig 9.
Failure to recover color performance in very severe color change scenarios.