Abstract:
Marine engineering and aquatic robotics have made underwater image enhancement popular. Recently, many underwater image enhancement algorithms have been proposed. These algorithms are mostly tested on synthetic datasets or a few real-world images.
Thus, it is unclear how these algorithms would perform on wild images and how we could measure field progress. The first comprehensive perceptual study and analysis of underwater image enhancement using large-scale real-world images fills this gap.
This project creates an Underwater Image Enhancement Benchmark (UIEB) with 950 real-world underwater images and 890 reference images. The remaining 60 underwater images without reference images are challenging data.
We quantitatively and qualitatively study state-of-the-art underwater image enhancement algorithms using this dataset. As a baseline, we propose an underwater image enhancement network (Water-Net) trained on this benchmark to demonstrate the generalization of the proposed UIEB for training CNNs.
The benchmark evaluations and proposed Water-Net show the performance and limitations of state-of-the-art algorithms, illuminating underwater image enhancement research. This https URL has the dataset and code.
Note: Please discuss with our team before submitting this abstract to the college. This Abstract or Synopsis varies based on student project requirements.
Did you like this final year project?
To download this project Code with thesis report and project training... Click Here
